-
-

Welcome to XuanPolicy’s documentation!

-

XuanPolicy is an open-source ensemble of Deep Reinforcement Learning (DRL) algorithm implementations.

+
+

Welcome to XuanCe’s documentation!

+

XuanCe is an open-source ensemble of Deep Reinforcement Learning (DRL) algorithm implementations.

We call it as Xuan-Ce (玄策) in Chinese. “Xuan (玄)” means incredible and magic box, “Ce (策)” means policy.

DRL algorithms are sensitive to hyper-parameters tuning, varying in performance with different tricks, @@ -119,10 +119,10 @@

Welcome to XuanPolicy’s documentation!TensorFlow, and MindSpore, and hope it can really become a zoo full of DRL algorithms.

-

Currently, THe XuanPolicy has been open-sourced on GitHub and OpenI:

+

Currently, THe XuanCe has been open-sourced on GitHub and OpenI:

-
GitHub： https://github.com/agi-brain/xuanpolicy.git
-
OpenI： https://github.com/agi-brain/xuanpolicy.git
+
GitHub： https://github.com/agi-brain/xuance.git
+
OpenI： https://github.com/agi-brain/xuance.git

How to use:

@@ -183,7 +183,7 @@

Indices and tables -

© Copyright 2023, XuanPolicy contributors.

+

© Copyright 2023, XuanCe contributors.

Built with Sphinx using a diff --git a/docs/build/html/search.html b/docs/build/html/search.html index 96c5d59af..a5b4f2105 100644 --- a/docs/build/html/search.html +++ b/docs/build/html/search.html @@ -3,7 +3,7 @@ - Search — XuanPolicy v0.1.11 documentation + Search — XuanCe v0.1.11 documentation @@ -40,7 +40,7 @@ - XuanPolicy + XuanCe
@@ -89,7 +89,7 @@
@@ -126,7 +126,7 @@
-

© Copyright 2023, XuanPolicy contributors.

+

© Copyright 2023, XuanCe contributors.

Built with Sphinx using a diff --git a/docs/build/html/searchindex.js b/docs/build/html/searchindex.js index 156da5cd5..4d086403a 100644 --- a/docs/build/html/searchindex.js +++ b/docs/build/html/searchindex.js @@ -1 +1 @@ -Search.setIndex({"docnames": ["documents/algorithms/drl/a2c", "documents/algorithms/drl/c51", "documents/algorithms/drl/ddpg", "documents/algorithms/drl/ddqn", "documents/algorithms/drl/dqn", "documents/algorithms/drl/drqn", "documents/algorithms/drl/dueldqn", "documents/algorithms/drl/mpdqn", "documents/algorithms/drl/noisydqn", "documents/algorithms/drl/pdqn", "documents/algorithms/drl/perdqn", "documents/algorithms/drl/ppg", "documents/algorithms/drl/ppo", "documents/algorithms/drl/qrdqn", "documents/algorithms/drl/sac", "documents/algorithms/drl/sac_dis", "documents/algorithms/drl/spdqn", "documents/algorithms/drl/td3", "documents/algorithms/drl/vpg", "documents/algorithms/index_drl", "documents/algorithms/index_marl", "documents/algorithms/marl/coma", "documents/algorithms/marl/dcg", "documents/algorithms/marl/iddpg", "documents/algorithms/marl/ippo", "documents/algorithms/marl/iql", "documents/algorithms/marl/isac", "documents/algorithms/marl/maddpg", "documents/algorithms/marl/mappo", "documents/algorithms/marl/masac", "documents/algorithms/marl/matd3", "documents/algorithms/marl/mfac", "documents/algorithms/marl/mfq", "documents/algorithms/marl/qmix", "documents/algorithms/marl/qtran", "documents/algorithms/marl/vdac", "documents/algorithms/marl/vdn", "documents/algorithms/marl/wqmix", "documents/api/agents", "documents/api/agents/drl/a2c", "documents/api/agents/drl/basic_drl_class", "documents/api/agents/drl/c51", "documents/api/agents/drl/ddpg", "documents/api/agents/drl/ddqn", "documents/api/agents/drl/dqn", "documents/api/agents/drl/dueldqn", "documents/api/agents/drl/mpdqn", "documents/api/agents/drl/noisydqn", "documents/api/agents/drl/pdqn", "documents/api/agents/drl/perdqn", "documents/api/agents/drl/pg", "documents/api/agents/drl/ppg", "documents/api/agents/drl/ppo_clip", "documents/api/agents/drl/ppo_kl", "documents/api/agents/drl/qrdqn", "documents/api/agents/drl/sac", "documents/api/agents/drl/sac_dis", "documents/api/agents/drl/spdqn", "documents/api/agents/drl/td3", "documents/api/agents/marl/basic_marl_class", "documents/api/agents/marl/coma", "documents/api/agents/marl/dcg", "documents/api/agents/marl/iddpg", "documents/api/agents/marl/ippo", "documents/api/agents/marl/iql", "documents/api/agents/marl/isac", "documents/api/agents/marl/maddpg", "documents/api/agents/marl/mappo", "documents/api/agents/marl/masac", "documents/api/agents/marl/matd3", "documents/api/agents/marl/mfac", "documents/api/agents/marl/mfq", "documents/api/agents/marl/qmix", "documents/api/agents/marl/qtran", "documents/api/agents/marl/vdac", "documents/api/agents/marl/vdn", "documents/api/agents/marl/wqmix", "documents/api/common", "documents/api/common/common_tools", "documents/api/common/memory_tools", "documents/api/common/memory_tools_marl", "documents/api/common/segtree_tool", "documents/api/common/statistic_tools", "documents/api/configs", "documents/api/environments", "documents/api/learners", "documents/api/learners/drl/a2c", "documents/api/learners/drl/c51", "documents/api/learners/drl/ddpg", "documents/api/learners/drl/ddqn", "documents/api/learners/drl/dqn", "documents/api/learners/drl/dueldqn", "documents/api/learners/drl/mpdqn", "documents/api/learners/drl/noisydqn", "documents/api/learners/drl/pdqn", "documents/api/learners/drl/perdqn", "documents/api/learners/drl/pg", "documents/api/learners/drl/ppg", "documents/api/learners/drl/ppo_clip", "documents/api/learners/drl/ppo_kl", "documents/api/learners/drl/qrdqn", "documents/api/learners/drl/sac", "documents/api/learners/drl/sac_dis", "documents/api/learners/drl/spdqn", "documents/api/learners/drl/td3", "documents/api/learners/learner", "documents/api/learners/marl/coma", "documents/api/learners/marl/dcg", "documents/api/learners/marl/iddpg", "documents/api/learners/marl/ippo", "documents/api/learners/marl/iql", "documents/api/learners/marl/isac", "documents/api/learners/marl/maddpg", "documents/api/learners/marl/mappo", "documents/api/learners/marl/masac", "documents/api/learners/marl/matd3", "documents/api/learners/marl/mfac", "documents/api/learners/marl/mfq", "documents/api/learners/marl/qmix", "documents/api/learners/marl/qtran", "documents/api/learners/marl/vdac", "documents/api/learners/marl/vdn", "documents/api/learners/marl/wqmix", "documents/api/policies", "documents/api/policies/categorical", "documents/api/policies/categorical_marl", "documents/api/policies/coordination_graph", "documents/api/policies/deterministic", "documents/api/policies/deterministic_marl", "documents/api/policies/gaussian", "documents/api/policies/gaussian_marl", "documents/api/policies/mixers", "documents/api/representations", "documents/api/representations/cnn", "documents/api/representations/mlp", "documents/api/representations/rnn", "documents/api/runners", "documents/api/runners/runner_basic", "documents/api/runners/runner_drl", "documents/api/runners/runner_football", "documents/api/runners/runner_magent", "documents/api/runners/runner_pettingzoo", "documents/api/runners/runner_sc2", "documents/api/utils", "documents/api/utils/distributions", "documents/api/utils/input_reformat", "documents/api/utils/layers", "documents/api/utils/operations", "documents/api/utils/value_norm", "documents/benchmark/atari", "documents/benchmark/magent", "documents/benchmark/mpe", "documents/benchmark/mujoco", "documents/benchmark/toy", "documents/usage/basic_usage", "documents/usage/installation", "documents/usage/professional_usage", "index"], "filenames": ["documents/algorithms/drl/a2c.rst", "documents/algorithms/drl/c51.rst", "documents/algorithms/drl/ddpg.rst", "documents/algorithms/drl/ddqn.rst", "documents/algorithms/drl/dqn.rst", "documents/algorithms/drl/drqn.rst", "documents/algorithms/drl/dueldqn.rst", "documents/algorithms/drl/mpdqn.rst", "documents/algorithms/drl/noisydqn.rst", "documents/algorithms/drl/pdqn.rst", "documents/algorithms/drl/perdqn.rst", "documents/algorithms/drl/ppg.rst", "documents/algorithms/drl/ppo.rst", "documents/algorithms/drl/qrdqn.rst", "documents/algorithms/drl/sac.rst", "documents/algorithms/drl/sac_dis.rst", "documents/algorithms/drl/spdqn.rst", "documents/algorithms/drl/td3.rst", "documents/algorithms/drl/vpg.rst", "documents/algorithms/index_drl.rst", "documents/algorithms/index_marl.rst", "documents/algorithms/marl/coma.rst", "documents/algorithms/marl/dcg.rst", "documents/algorithms/marl/iddpg.rst", "documents/algorithms/marl/ippo.rst", "documents/algorithms/marl/iql.rst", "documents/algorithms/marl/isac.rst", "documents/algorithms/marl/maddpg.rst", "documents/algorithms/marl/mappo.rst", "documents/algorithms/marl/masac.rst", "documents/algorithms/marl/matd3.rst", "documents/algorithms/marl/mfac.rst", "documents/algorithms/marl/mfq.rst", "documents/algorithms/marl/qmix.rst", "documents/algorithms/marl/qtran.rst", "documents/algorithms/marl/vdac.rst", "documents/algorithms/marl/vdn.rst", "documents/algorithms/marl/wqmix.rst", "documents/api/agents.rst", "documents/api/agents/drl/a2c.rst", "documents/api/agents/drl/basic_drl_class.rst", "documents/api/agents/drl/c51.rst", "documents/api/agents/drl/ddpg.rst", "documents/api/agents/drl/ddqn.rst", "documents/api/agents/drl/dqn.rst", "documents/api/agents/drl/dueldqn.rst", "documents/api/agents/drl/mpdqn.rst", "documents/api/agents/drl/noisydqn.rst", "documents/api/agents/drl/pdqn.rst", "documents/api/agents/drl/perdqn.rst", "documents/api/agents/drl/pg.rst", "documents/api/agents/drl/ppg.rst", "documents/api/agents/drl/ppo_clip.rst", "documents/api/agents/drl/ppo_kl.rst", "documents/api/agents/drl/qrdqn.rst", "documents/api/agents/drl/sac.rst", "documents/api/agents/drl/sac_dis.rst", "documents/api/agents/drl/spdqn.rst", "documents/api/agents/drl/td3.rst", "documents/api/agents/marl/basic_marl_class.rst", "documents/api/agents/marl/coma.rst", "documents/api/agents/marl/dcg.rst", "documents/api/agents/marl/iddpg.rst", "documents/api/agents/marl/ippo.rst", "documents/api/agents/marl/iql.rst", "documents/api/agents/marl/isac.rst", "documents/api/agents/marl/maddpg.rst", "documents/api/agents/marl/mappo.rst", "documents/api/agents/marl/masac.rst", "documents/api/agents/marl/matd3.rst", "documents/api/agents/marl/mfac.rst", "documents/api/agents/marl/mfq.rst", "documents/api/agents/marl/qmix.rst", "documents/api/agents/marl/qtran.rst", "documents/api/agents/marl/vdac.rst", "documents/api/agents/marl/vdn.rst", "documents/api/agents/marl/wqmix.rst", "documents/api/common.rst", "documents/api/common/common_tools.rst", "documents/api/common/memory_tools.rst", "documents/api/common/memory_tools_marl.rst", "documents/api/common/segtree_tool.rst", "documents/api/common/statistic_tools.rst", "documents/api/configs.rst", "documents/api/environments.rst", "documents/api/learners.rst", "documents/api/learners/drl/a2c.rst", "documents/api/learners/drl/c51.rst", "documents/api/learners/drl/ddpg.rst", "documents/api/learners/drl/ddqn.rst", "documents/api/learners/drl/dqn.rst", "documents/api/learners/drl/dueldqn.rst", "documents/api/learners/drl/mpdqn.rst", "documents/api/learners/drl/noisydqn.rst", "documents/api/learners/drl/pdqn.rst", "documents/api/learners/drl/perdqn.rst", "documents/api/learners/drl/pg.rst", "documents/api/learners/drl/ppg.rst", "documents/api/learners/drl/ppo_clip.rst", "documents/api/learners/drl/ppo_kl.rst", "documents/api/learners/drl/qrdqn.rst", "documents/api/learners/drl/sac.rst", "documents/api/learners/drl/sac_dis.rst", "documents/api/learners/drl/spdqn.rst", "documents/api/learners/drl/td3.rst", "documents/api/learners/learner.rst", "documents/api/learners/marl/coma.rst", "documents/api/learners/marl/dcg.rst", "documents/api/learners/marl/iddpg.rst", "documents/api/learners/marl/ippo.rst", "documents/api/learners/marl/iql.rst", "documents/api/learners/marl/isac.rst", "documents/api/learners/marl/maddpg.rst", "documents/api/learners/marl/mappo.rst", "documents/api/learners/marl/masac.rst", "documents/api/learners/marl/matd3.rst", "documents/api/learners/marl/mfac.rst", "documents/api/learners/marl/mfq.rst", "documents/api/learners/marl/qmix.rst", "documents/api/learners/marl/qtran.rst", "documents/api/learners/marl/vdac.rst", "documents/api/learners/marl/vdn.rst", "documents/api/learners/marl/wqmix.rst", "documents/api/policies.rst", "documents/api/policies/categorical.rst", "documents/api/policies/categorical_marl.rst", "documents/api/policies/coordination_graph.rst", "documents/api/policies/deterministic.rst", "documents/api/policies/deterministic_marl.rst", "documents/api/policies/gaussian.rst", "documents/api/policies/gaussian_marl.rst", "documents/api/policies/mixers.rst", "documents/api/representations.rst", "documents/api/representations/cnn.rst", "documents/api/representations/mlp.rst", "documents/api/representations/rnn.rst", "documents/api/runners.rst", "documents/api/runners/runner_basic.rst", "documents/api/runners/runner_drl.rst", "documents/api/runners/runner_football.rst", "documents/api/runners/runner_magent.rst", "documents/api/runners/runner_pettingzoo.rst", "documents/api/runners/runner_sc2.rst", "documents/api/utils.rst", "documents/api/utils/distributions.rst", "documents/api/utils/input_reformat.rst", "documents/api/utils/layers.rst", "documents/api/utils/operations.rst", "documents/api/utils/value_norm.rst", "documents/benchmark/atari.rst", "documents/benchmark/magent.rst", "documents/benchmark/mpe.rst", "documents/benchmark/mujoco.rst", "documents/benchmark/toy.rst", "documents/usage/basic_usage.rst", "documents/usage/installation.rst", "documents/usage/professional_usage.rst", "index.rst"], "titles": ["A2C: Advantage Actor-Critic", "C51", "DDPG: Deep Deterministic Policy Gradient", "DDQN: Double Deep Q-Networks", "DQN", "DRQN", "Duel DQN", "MPDQN", "Noisy DQN", "PDQN", "Per DQN", "PPG", "PPO: Proximal Policy Optimization", "QRDQN", "Soft Actor-Critic", "Soft Actor-Critic for discrete action space", "SPDQN", "TD3", "Vanilla Policy Gradient", "Deep Reinforcement Learning", "Multi-Agent Reinforcement Learning", "COMA", "DCG", "IDDPG", "IPPO", "IQL: Independent Q-Learning", "ISAC", "MADDPG", "MAPPO", "MASAC", "MATD3", "MFAC", "MFQ", "QMIX", "QTRAN", "VDAC", "VDN: Value Decomposition Networks", "Weighted QMIX", "Agents", "A2C_Agent", "Agent", "C51_Agent", "DDPG_Agent", "DDQN_Agent", "DQN_Agent", "DuelDQN_Agent", "MPDQN_Agent", "NoisyDQN_Agent", "PDQN_Agent", "PerDQN_Agent", "PG_Agent", "PPG_Agent", "PPOCLIP_Agent", "PPOKL_Agent", "QRDQN_Agent", "SAC_Agent", "SACDIS_Agent", "SPDQN_Agent", "TD3_Agent", "MARLAgent", "COMA_Agents", "DCG_Agents", "IDDPG_Agents", "IPPO_Agents", "IQL_Agents", "ISAC_Agents", "MADDPG_Agents", "MAPPO_Agents", "MASAC_Agents", "MATD3_Agents", "MFAC", "MFQ_Agents", "QMIX_Agents", "QTRAN_Agents", "VDAC", "VDN_Agents", "WQMIX_Agents", "Common", "Common Tools", "Memory", "Memory for MARL", "Segment Tree", "Statistic Tools", "Configs", "Environments", "Learners", "A2C_Learner", "C51_Learner", "DDPG_Learner", "DDQN_Learner", "DQN_Learner", "DuelDQN_Learner", "MPDQN_Learner", "NoisyDQN_Learner", "PDQN_Learner", "PerDQN_Learner", "PG_Learner", "PPG_Learner", "PPOCLIP_Learner", "PPOKL_Learner", "QRDQN_Learner", "SAC_Learner", "SACDIS_Learner", "SPDQN_Learner", "TD3_Learner", "Learner", "COMA_Learner", "DCG_Learner", "IDDPG_Learner", "IPPO_Learner", "IQL_Learner", "ISAC_Learner", "MADDPG_Learner", "MAPPO_Learner", "MASAC_Learner", "MATD3_Learner", "MFAC_Learner", "MFQ_Learner", "QMIX_Learner", "QTRAN_Learner", "VDAC_Learner", "VDN_Learner", "WQMIX_Learner", "Policies", "Categorical", "Categorical-MARL", "Coordination-Graph", "Deterministic", "Deterministic-MARL", "Gaussian", "Gaussian-MARL", "Mixiers", "Representations", "CNN-based", "MLP-based", "RNN-based", "Runners", "Runner_Base", "Runner_DRL", "Runner_Football", "Runner_MAgent", "Runner_Pettingzoo", "Runner_SC2", "Utils", "Distributions", "Input Reformation", "Neural Network Layers", "Operations", "ValueNorm", "Atari benchmarks", "Magent benchmarks", "MPE benchmarks", "MuJoCo benchmarks", "Toy benchmarks", "Quick Start", "Installation", "Professional Usage", "Welcome to XuanPolicy\u2019s documentation!"], "terms": {"deep": [4, 5, 38, 85, 134, 136, 155, 156, 157], "q": [4, 5, 19, 20, 38, 43, 46, 48, 57, 85], "network": [4, 5, 19, 20, 38, 39, 50, 51, 52, 53, 85, 132, 133, 134, 135], "i": [4, 5, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 84, 105, 133, 134, 135, 154, 155, 156, 157], "valu": [4, 5, 20, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 67, 83, 85, 105, 123, 143], "base": [4, 5, 84, 123, 143, 156], "drl": [4, 5, 156, 157], "paper": [4, 5], "link": [4, 5, 154, 156], "human": [4, 46, 48, 57, 83, 156], "level": [4, 156], "control": [4, 84], "through": 4, "reinforc": [4, 38, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 85, 123, 136, 156, 157], "learn": [4, 5, 38, 39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 85, 105, 123, 136, 155, 156, 157], "bibtex": [4, 5], "citat": [4, 5], "articl": 4, "mnih2015human": 4, "titl": [4, 5], "author": [4, 5], "mnih": 4, "volodymyr": 4, "kavukcuoglu": 4, "korai": 4, "silver": 4, "david": 4, "rusu": 4, "andrei": 4, "A": [4, 133, 156], "veness": 4, "joel": 4, "bellemar": 4, "marc": 4, "g": 4, "grave": 4, "alex": 4, "riedmil": 4, "martin": 4, "fidjeland": 4, "andrea": 4, "k": [4, 40, 62, 65, 66, 68, 69, 133], "ostrovski": 4, "georg": 4, "other": 4, "journal": 4, "natur": 4, "volum": 4, "518": 4, "number": [4, 39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 83, 133, 156], "7540": 4, "page": [4, 156, 157], "529": 4, "533": 4, "year": [4, 5], "2015": [4, 5], "publish": [4, 152], "group": [4, 40], "dqn": [5, 19, 38, 43, 44, 45, 47, 83, 85, 154], "recurr": [5, 132, 135], "partial": 5, "observ": [5, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 133, 134, 156], "mdp": 5, "inproceed": 5, "hausknecht2015deep": 5, "hausknecht": 5, "matthew": 5, "stone": 5, "peter": 5, "booktitl": 5, "aaai": 5, "fall": 5, "symposium": 5, "seri": 5, "c51": 19, "ddqn": 19, "doubl": [19, 38, 43, 85], "duel": [19, 38, 45, 85], "noisi": [19, 38, 47, 85], "per": [19, 40, 156], "qrdqn": [19, 38, 54, 85], "drqn": 19, "vanilla": [19, 38, 85], "polici": [19, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 85, 105, 143, 154, 156, 157], "gradient": [19, 38, 85], "ppg": [19, 38, 51, 59, 85], "ppo": [19, 38, 52, 53, 85, 152, 156], "proxim": [19, 38, 85], "optim": [19, 38, 39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 85, 105, 156], "pdqn": [19, 38, 48, 85], "spdqn": [19, 38, 57, 85], "mpdqn": [19, 38, 46, 85], "a2c": [19, 38, 39, 59, 85, 152], "advantag": [19, 38, 85], "actor": [19, 38, 42, 55, 56, 58, 60, 67, 85, 133, 143], "critic": [19, 38, 39, 42, 50, 51, 52, 53, 55, 56, 58, 60, 67, 85, 133, 143], "soft": [19, 38, 85], "td3": [19, 38, 58, 85, 152], "ddpg": [19, 38, 42, 85, 152], "determinist": [19, 38, 85, 123], "iql": [20, 38, 85], "independ": [20, 38, 85], "vdn": [20, 38, 85], "decomposit": [20, 38, 85, 123], "qtran": [20, 38, 85], "qmix": [20, 38, 85], "weight": [20, 38, 49, 85, 133], "dcg": [20, 38, 85], "mfq": [20, 38, 85], "mfac": [20, 38, 59, 85], "mappo": [20, 38, 85], "coma": [20, 38, 59, 60, 85], "isac": [20, 38, 85], "masac": [20, 38, 85], "iddpg": [20, 38, 85, 154], "maddpg": [20, 38, 85, 154], "matd3": [20, 38, 85], "vdac": [20, 38, 59, 85], "pytorch": [38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 133, 134, 135, 155, 157], "tensorflow": [38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 133, 134, 135, 155, 157], "mindspor": [38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 133, 134, 135, 155, 156, 157], "checkmark": [38, 85], "c51dqn": [38, 41, 85], "distribut": [38, 51, 53, 85, 143], "paramet": [38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 85, 105, 133, 134, 135, 154, 156, 157], "space": [19, 38, 40, 46, 48, 57, 85, 123, 156], "nois": [38, 42, 58, 59, 62, 65, 66, 68, 69, 85], "perdqn": [38, 49, 85], "priorit": [38, 85], "experi": [38, 85], "replai": [38, 40, 59, 85], "quantil": [38, 85], "regress": [38, 85], "vpg": [38, 85], "phasic": [38, 85], "parameteris": [38, 85], "split": [38, 85], "multi": [38, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 85, 123, 132, 133, 134, 157], "pass": [38, 39, 41, 43, 44, 45, 46, 47, 48, 49, 50, 52, 53, 54, 56, 57, 85, 105], "sac": [38, 55, 85], "di": [38, 85], "discret": [19, 38, 46, 48, 57, 85, 123], "action": [19, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 83, 84, 85, 105, 123, 156], "twin": [38, 85], "delai": [38, 85], "mixer": [38, 72, 73, 75, 76, 85, 123], "wqmix": [38, 85], "transform": [38, 85], "coordin": [38, 85, 123], "graph": [38, 85, 123], "ippo": [20, 38, 85], "counterfacut": [38, 85], "pg": [38, 50, 59, 85], "mean": [38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 71, 85, 156, 157], "field": [38, 85], "class": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135], "xuanpolici": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 133, 134, 135, 152, 154, 155, 156], "torch": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 133, 134, 135, 154, 155, 156], "agent": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 84, 85, 123, 136, 154, 156, 157], "policy_gradi": [39, 42, 46, 48, 50, 51, 52, 53, 55, 56, 57, 58], "config": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 154, 157], "env": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 84, 154, 156], "schedul": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 105, 156], "devic": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 133, 134, 135, 156], "namespac": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105], "provid": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 135, 156], "hyper": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156, 157], "environ": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 136, 154, 155, 156, 157], "vector_env": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84], "vecenv": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84], "The": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135, 154, 155, 156], "vector": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 133, 134, 135, 136, 156], "nn": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 105, 133, 134, 135, 156], "modul": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 105, 133, 134, 135, 156, 157], "updat": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105], "lr_schedul": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 105, 156], "_lrschedul": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 105], "implement": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 84, 133, 134, 135, 156, 157], "rate": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 105, 156], "decai": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 105, 156], "str": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135, 156], "int": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 133, 134, 135, 156], "choos": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135, 154, 155], "cpu": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 133, 134, 135], "gpu": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 133, 134, 135], "train": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 133, 134, 135, 154, 156, 157], "model": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 133, 134, 135, 154], "_action": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "ob": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59], "calcul": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 133, 134, 135, 156], "accord": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 134, 154], "numpi": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 133, 134, 156], "ndarrai": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 133, 134], "current": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 71, 133, 134, 135, 156, 157], "step": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 64, 67, 71, 72, 73, 75, 76, 83, 84, 133, 134, 135, 155], "return": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135, 156], "v": [39, 40, 50, 51, 52, 53], "execut": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 59, 154], "type": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 133, 134, 135, 155, 156], "np": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 133, 134, 156], "train_step": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 156], "test": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 156], "env_fn": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 156], "test_episod": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 83, 156], "function": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 105, 133, 134, 135, 156], "make": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 156], "episod": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 62, 65, 66, 68, 69, 156], "score": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 156], "accumul": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "list": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 84, 143], "import": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 84, 105, 133, 134, 135, 154, 155, 156], "from": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135, 156, 157], "def": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135, 156], "__init__": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135], "self": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135], "dummyvecenv_gym": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "option": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 133, 134, 135], "none": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 133, 134, 135, 156], "union": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 133, 134, 135], "render": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 83, 84, 156], "n_env": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 67, 156], "num_env": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156], "n_step": [39, 40, 50, 51, 52, 53, 156], "n_epoch": [39, 50, 51, 52, 53, 60, 67, 156], "n_minibatch": [39, 50, 51, 52, 53, 60, 67, 156], "gamma": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 156], "gae_lam": [39, 50, 51, 52, 53], "gae_lambda": [39, 50, 51, 52, 53, 60, 67, 156], "clip_grad": [39, 50], "observation_spac": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156], "action_spac": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 156], "auxiliary_info_shap": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "atari": [39, 41, 43, 44, 45, 47, 49, 50, 52, 53, 54, 56, 83, 84, 133, 157], "true": [39, 40, 41, 43, 44, 45, 46, 47, 48, 49, 50, 52, 53, 54, 56, 57, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 83, 135, 154, 156], "env_nam": [39, 41, 43, 44, 45, 47, 49, 50, 52, 53, 54, 56, 61, 83, 154, 156], "els": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 135, 156], "fals": [39, 40, 41, 43, 44, 45, 46, 47, 48, 49, 50, 52, 53, 54, 56, 57, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 135, 154, 156], "buffer": [39, 40, 41, 43, 44, 45, 47, 50, 52, 53, 54, 56, 59, 60, 61, 64, 67, 72, 75, 76], "dummyonpolicybuffer_atari": [39, 50, 52, 53], "dummyonpolicybuff": [39, 50, 51, 52], "buffer_s": [39, 50, 51, 52, 53, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "batch_siz": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83], "memori": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 77], "use_ga": [39, 50, 51, 52, 53, 60, 67, 156], "use_advnorm": [39, 50, 51, 52, 53, 60, 67, 156], "learner": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 157], "a2c_learn": 39, "model_dir": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 156], "vf_coef": [39, 52, 53, 156], "ent_coef": [39, 50, 51, 52, 53, 156], "super": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 133, 134, 135], "log_dir": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 156], "_": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 64, 65, 66, 67, 68, 69, 72, 75, 76], "dist": [39, 50, 51, 52, 53, 65, 67, 68], "act": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 105], "stochastic_sampl": [39, 50, 51, 52, 53, 67], "detach": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 135], "buf_ob": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "tqdm": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "rang": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 67, 156], "step_info": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "obs_rm": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 105], "_process_observ": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "val": [39, 51, 52, 53], "next_ob": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "reward": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "termin": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 155], "trunction": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "info": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "store": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 84, 154], "_process_reward": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "full": [39, 50, 51, 52, 53, 60, 67, 157], "finish_path": [39, 50, 51, 52, 53], "0": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 84, 105, 133, 134, 135, 156], "index": [39, 50, 51, 52, 53, 60, 67, 135, 156, 157], "arang": [39, 50, 51, 52, 53, 60, 67], "random": [39, 41, 42, 43, 44, 45, 46, 48, 49, 50, 51, 52, 53, 54, 57, 58, 59, 60, 61, 62, 64, 66, 67, 69, 71, 72, 75, 76, 136, 156], "shuffl": [39, 50, 51, 52, 53, 60, 67], "start": [39, 50, 51, 52, 53, 59, 60, 67, 155, 156, 157], "end": [39, 50, 51, 52, 53, 59, 60, 67, 156], "sample_idx": [39, 50, 51, 52, 53, 60, 67], "obs_batch": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "act_batch": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "ret_batch": [39, 50, 51, 52, 53], "adv_batch": [39, 51, 52, 53], "sampl": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84], "log_info": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "current_step": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 156], "clear": [39, 50, 51, 52, 53, 60, 67], "ret_rm": [39, 40, 42, 46, 48, 50, 52, 53, 55, 56, 57, 58], "1": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 84, 105, 133, 134, 135, 152, 154, 155], "reset_ob": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "current_episod": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "use_wandb": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "d": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 156], "episode_step": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "episode_scor": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "test_env": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "video": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "episode_video": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "best_scor": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "inf": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "reset": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 84, 156], "render_mod": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 83, 156], "rgb_arrai": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 83, 156], "imag": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 133], "idx": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "img": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "enumer": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "append": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 62, 65, 66, 68, 69, 133], "while": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "ret": [39, 51, 52, 53], "copi": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 156], "test_mod": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 83, 156], "print": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 105, 156], "2f": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 156], "time": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 84, 105], "height": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 133], "width": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 133], "channel": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 133], "videos_info": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "videos_test": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "arrai": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 62, 65, 66, 68, 69, 71], "dtype": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 133, 134], "uint8": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "transpos": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 133], "4": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 83, 105, 152, 155], "2": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 61, 67, 69, 71, 83, 84, 105, 133, 152, 154, 155], "3": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 83, 105, 133, 152, 155], "log_video": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "fp": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "50": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "x_index": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "best": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 156], "test_info": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "std": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 156], "close": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 84, 156], "To": [40, 59, 84, 105, 133, 134, 135], "creat": [40, 59, 60, 67, 84, 105, 133, 134, 135, 136, 143, 154, 155], "new": [40, 59, 105, 135, 155], "you": [40, 59, 84, 105, 133, 134, 135, 154, 155, 156], "should": [40, 59, 105, 155, 156], "build": [40, 59, 60, 67, 105, 154, 156], "inherit": [40, 59, 84, 105], "common": [40, 59, 156, 157], "memory_tool": [40, 59], "experic": [40, 59], "directori": [40, 59, 84, 105, 154, 155, 156], "log": [40, 52, 59, 83, 154, 156], "file": [40, 59, 84, 105, 134, 154], "default": [40, 59, 83, 105, 156], "save_model": [40, 46, 48, 57, 59, 105, 156], "model_nam": [40, 59, 105, 156], "save": [40, 46, 48, 57, 59, 84, 105, 154, 156], "": [40, 59, 105, 133, 154], "name": [40, 59, 84, 134, 154, 156], "load_model": [40, 46, 48, 57, 59, 105, 156], "path": [40, 59, 105, 154, 156], "seed": [40, 59, 83, 84, 105, 136, 156], "load": [40, 59, 105, 156], "specifi": [40, 59, 105, 133, 134, 135, 154], "where": [40, 59, 105], "select": [40, 59, 60, 61, 64, 67, 71, 72, 75, 76, 105, 135], "wa": [40, 59, 105], "exit": [40, 59, 105], "visual": [40, 154], "inform": [40, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 135, 154, 156], "via": 40, "wandb": [40, 83, 154, 156], "tensorboard": [40, 83, 154, 156], "dict": [40, 46, 48, 57, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 133, 134, 135], "interact": 40, "between": 40, "upload": 40, "frame": [40, 83], "second": 40, "normal": [40, 42, 58, 62, 66, 69, 133, 134, 135, 143, 156], "origin": [40, 134], "get": [40, 59, 60, 67, 135, 143], "finish": [40, 156], "tensorflowtensorflow": 40, "mindsporetensorflow": 40, "abc": [40, 105], "comm": [40, 46, 48, 57], "mpi": [40, 46, 48, 57], "comm_world": [40, 46, 48, 57], "runningmeanstd": [40, 46, 48, 57], "shape": [40, 42, 46, 48, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 133, 134, 135], "space2shap": [40, 46, 48, 57, 156], "use_mpi": [40, 46, 48, 57], "use_obsnorm": [40, 46, 48, 57, 83, 156], "use_rewnorm": [40, 46, 48, 57, 83, 156], "obsnorm_rang": [40, 46, 48, 57, 83, 156], "rewnorm_rang": [40, 46, 48, 57, 83, 156], "zero": [40, 46, 48, 57, 135], "float32": [40, 46, 48, 57, 59, 133, 134], "time_str": 40, "asctim": 40, "replac": 40, "f": [40, 105, 133, 156], "seed_": [40, 105], "model_dir_sav": [40, 59], "o": [40, 59, 105, 156], "join": [40, 59, 105, 156], "getcwd": [40, 156], "exist": [40, 105, 156], "makedir": 40, "logger": [40, 83, 156], "writer": [40, 59], "summarywrit": [40, 59], "elif": [40, 73], "config_dict": 40, "var": 40, "wandb_dir": 40, "init": [40, 133, 156], "project": [40, 157], "project_nam": [40, 83, 156], "entiti": 40, "wandb_user_nam": [40, 83, 154, 156], "note": [40, 155], "socket": 40, "gethostnam": 40, "dir": 40, "env_id": [40, 83, 84, 154, 156], "job_typ": 40, "reinit": 40, "wandb_sil": 40, "rais": [40, 59, 73, 105], "No": 40, "model_dir_load": [40, 59, 156], "create_directori": [40, 59], "int32": [40, 46, 48, 57, 59], "model_path": [40, 59, 105], "item": 40, "try": 40, "add_scalar": 40, "except": 40, "format": [40, 73], "gif": 40, "add_video": 40, "global_step": 40, "isinst": [40, 46, 48, 57], "kei": [40, 46, 48, 57], "clip": [40, 42, 46, 48, 57, 58, 62, 65, 66, 68, 69], "ep": [40, 46, 48, 57, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156], "100": [40, 46, 48, 57], "abstractmethod": [40, 105], "notimplementederror": [40, 59, 105], "tk": [40, 59], "logdir": [40, 59, 154], "modeldir": [40, 59], "cell": [40, 59, 135], "qlearning_famili": [41, 43, 44, 45, 47, 49, 54], "egreedi": [41, 43, 44, 45, 46, 47, 48, 49, 54, 57, 60, 61, 64, 71, 72, 73, 75, 76], "float": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 57, 58, 59, 71, 133], "epsilong": [41, 43, 44, 45, 46, 47, 48, 49, 54, 57], "greedi": [41, 43, 44, 45, 46, 47, 48, 49, 54, 57, 60, 61, 64, 67, 71, 72, 75, 76], "factor": [41, 43, 44, 45, 46, 47, 48, 49, 54, 57, 59], "train_frequ": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 55, 56, 57, 58], "training_frequ": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 55, 56, 57, 58, 59, 83], "start_train": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 55, 56, 57, 58, 59, 61, 64, 71, 72, 75, 76, 83], "start_greedi": [41, 43, 44, 45, 49, 54, 60, 61, 64, 71, 72, 73, 75, 76, 83], "end_greedi": [41, 43, 44, 45, 49, 54, 60, 61, 64, 71, 72, 73, 75, 76, 83], "dummyoffpolicybuffer_atari": [41, 43, 44, 45, 47, 54, 56], "dummyoffpolicybuff": [41, 42, 43, 44, 45, 46, 47, 48, 54, 55, 56, 57, 58], "n_size": [41, 42, 43, 44, 45, 47, 49, 54, 55, 56, 58, 60, 67, 83], "c51_learner": 41, "sync_frequ": [41, 43, 44, 45, 47, 49, 54, 60, 61, 64, 71, 72, 73, 75, 76, 83], "argmax_act": [41, 43, 44, 45, 47, 49, 54], "random_act": [41, 43, 44, 45, 49, 54, 59, 61, 64, 71, 72, 75, 76], "choic": [41, 43, 44, 45, 46, 48, 49, 54, 57, 61, 64, 72, 75, 76, 83, 134, 156], "n": [41, 43, 44, 45, 46, 48, 49, 54, 57, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 155], "rand": [41, 43, 44, 45, 46, 48, 49, 54, 57, 61, 64, 71, 72, 75, 76], "rew_batch": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 55, 56, 57, 58], "terminal_batch": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 55, 56, 57, 58], "next_batch": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 55, 56, 57, 58], "epsilon": [41, 43, 44, 45, 46, 48, 49, 54, 57, 59, 60, 61, 64, 67, 71, 72, 75, 76], "decay_step_greedi": [41, 43, 44, 45, 49, 54, 60, 61, 64, 71, 72, 73, 75, 76, 83], "noise_scal": [42, 46, 47, 48, 55, 56, 57, 58], "varianc": [42, 58], "gaussian": [42, 58, 123, 156], "sequenc": [42, 46, 48, 55, 56, 57, 58, 67, 105, 133, 134, 135], "start_nois": [42, 46, 47, 48, 55, 56, 57, 58], "end_nois": [42, 46, 47, 48, 55, 56, 57, 58], "delta_nois": 42, "running_step": [42, 58, 83, 105, 156], "ddpg_learner": 42, "tau": [42, 46, 48, 55, 56, 57, 58], "size": [42, 58, 62, 66, 69, 133, 135], "trick": [43, 83, 157], "ddqn_learner": 43, "dqn_learner": [44, 47], "dueldqn_learn": 45, "disact": [46, 48, 57], "conact": [46, 48, 57], "con_act": [46, 48, 57], "continu": [46, 48, 57, 123, 156], "pad_act": [46, 48, 57], "tupl": [46, 48, 57, 60, 61, 64, 67, 71, 72, 75, 76, 133, 135], "gym": [46, 48, 57, 83, 84, 156], "gym_env": [46, 48, 57], "old_a": [46, 48, 57], "num_disact": [46, 48, 57], "box": [46, 48, 57, 84, 157], "low": [46, 48, 57, 62, 65, 66, 68, 69], "high": [46, 48, 57, 62, 65, 66, 68, 69, 157], "action_high": [46, 48, 57], "action_low": [46, 48, 57], "action_rang": [46, 48, 57], "representation_info_shap": [46, 48, 50, 51, 53, 57, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76], "state": [46, 48, 57, 59, 60, 61, 64, 67, 71, 72, 75, 76, 133, 134, 135], "nenv": [46, 48, 57, 59, 61, 64, 72, 75, 76], "epsilon_step": [46, 48, 57], "1000": [46, 48, 57, 152], "epsilon_initi": [46, 48, 57], "epsilon_fin": [46, 48, 57], "buffer_action_spac": [46, 48, 57], "ones": [46, 48, 57, 156], "float64": [46, 48, 57], "nsize": [46, 48, 57], "batchsiz": [46, 48, 57], "pdqn_learner": [46, 48, 57], "conact_s": [46, 48, 57], "sum": [46, 48, 57, 71], "no_grad": [46, 48, 57, 61], "as_tensor": [46, 48, 57, 133, 134], "rnd": [46, 48, 57], "qeval": [46, 48, 57], "unsqueez": [46, 48, 57, 60, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "data": [46, 48, 57, 133, 135], "argmax": [46, 48, 57], "offset": [46, 48, 57], "10000": [46, 48, 57, 83, 156], "episode_info": [46, 48, 57], "concaten": [46, 48, 57], "axi": [46, 48, 57, 67], "ravel": [46, 48, 57], "end_episod": [46, 48, 57], "50000": [46, 48, 57], "npy": [46, 48, 57, 105], "count": [46, 48, 57], "test_step": [46, 48, 57, 83, 156], "evalu": [46, 48, 57], "decay_step_nois": 47, "update_nois": 47, "per_beta0": 49, "per_beta": 49, "peroffpolicybuff": 49, "per_alpha": 49, "perdqn_learn": 49, "td_error": 49, "update_prior": 49, "represent": [50, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 133, 134, 135, 143, 156, 157], "output_shap": [50, 51, 53, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 133, 134, 135], "pg_learner": 50, "stochast": [51, 53, 143], "policy_nepoch": 51, "value_nepoch": 51, "aux_nepoch": 51, "actor_represent": 51, "old_dist": [51, 53], "ppg_learner": 51, "clip_rang": [51, 52, 156], "kl_beta": 51, "split_distribut": [51, 53], "aux_batch": [51, 52, 53], "update_polici": 51, "update_crit": 51, "old_prob": 51, "buffer_ob": 51, "buffer_act": 51, "new_dist": 51, "auxiliary_info": 51, "update_auxiliari": 51, "logp": [51, 52, 53], "probabl": 52, "old_logp": [52, 53], "ppoclip_learn": 52, "clip_grad_norm": [52, 156], "use_grad_clip": [52, 156], "log_prob": [52, 67], "value_batch": [52, 53], "representation_actor": 53, "ppokl_learn": 53, "target_kl": [53, 156], "qrdqn_learner": 54, "sac_learn": 55, "act_dist": 55, "sacdi": 56, "sacdis_learn": 56, "act_prob": 56, "act_distribut": 56, "td3_learner": 58, "actor_update_delai": 58, "marl": [59, 77, 123], "agents_marl": [59, 60, 71, 73], "learnerma": [59, 105], "kwarg": [59, 105, 135], "joint": [59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "global": [59, 60, 67], "avail": [59, 60, 61, 64, 67, 72, 75, 76], "etc": [59, 84, 154, 155], "input": [59, 60, 67, 133, 134, 135, 143, 156], "info_train": [59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "linear_decay_or_increas": [59, 60, 71, 73], "step_length": 59, "increas": 59, "onc": 59, "randomag": 59, "arg": [59, 62, 66, 69, 71, 73, 105, 156], "output": [59, 62, 65, 66, 68, 69, 133, 134, 135], "object": 59, "dummyvecenv_pettingzoo": [59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "basebuff": 59, "n_agent": [59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105], "dim_ob": [59, 67, 105], "dim_act": [59, 60, 61, 64, 67, 71, 72, 73, 75, 76, 105], "dim_id": [59, 105], "cuda": [59, 83, 105, 156], "is_avail": [59, 105], "is_decai": 59, "delta": 59, "max": 59, "min": 59, "agent_kei": [59, 61, 62, 65, 66, 68, 69, 71, 73], "obs_n": [59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "rand_a": 59, "e": [59, 155], "handl": 59, "agent_index": 59, "agent_id": 59, "epsilon_decai": [59, 73], "agents_id": [59, 60, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "tile": 59, "expand_dim": 59, "ey": [59, 60, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "reshap": [59, 60, 64, 67, 72, 75, 76], "obs_in": [59, 60, 61, 64, 67, 71, 72, 75, 76], "id": [59, 105, 156], "greedy_act": [59, 61, 64, 71, 72, 75, 76], "random_vari": 59, "action_pick": 59, "i_episod": [59, 62, 65, 66, 68, 69, 73], "get_total_it": [59, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 156], "agent_nam": [59, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 154, 156], "ppo_clip": [59, 156], "ppo_kl": [59, 156], "mappo_clip": 59, "mappo_kl": 59, "training_step": 59, "nepoch": 59, "nminibatch": 59, "nstep": 59, "m": 59, "op": [59, 83], "tensor": [59, 60, 61, 62, 64, 66, 67, 69, 71, 72, 75, 76, 133, 134, 135], "dummyvecenv_ma": [59, 84], "expanddim": 59, "broadcast_to": 59, "view": [59, 60, 61, 64, 67, 72, 75, 76, 154], "asnumpi": 59, "a3c": 59, "mutli_agent_rl": [60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "rnn_hidden": [60, 61, 64, 67, 71, 72, 75, 76, 135], "avail_act": [60, 61, 64, 67, 72, 75, 76], "hidden": [60, 61, 64, 67, 71, 72, 75, 76, 133, 135], "rnn": [60, 61, 64, 67, 71, 72, 75, 76, 132, 143], "mask": [60, 61, 64, 67, 71, 72, 75, 76], "bool": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "hidden_st": [60, 61, 64, 67, 71, 72, 75, 76, 135], "actions_n": [60, 61, 64, 67, 71, 72, 75, 76], "onehot_act": [60, 71, 105], "next": [60, 61, 64, 67, 71, 72, 75, 76, 155], "onehot": 60, "i_step": [60, 61, 64, 67, 71, 72, 73, 75, 76], "th": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "dure": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156], "process": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 133, 134, 135, 154, 156, 157], "marlag": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "delta_egreedi": [60, 61, 64, 71, 72, 73, 75, 76], "state_spac": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "dim_stat": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84], "state_shap": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "input_represent": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "get_repre_in": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "use_recurr": [60, 61, 64, 67, 71, 72, 75, 76], "use_global_st": [60, 67], "kwargs_rnn": [60, 61, 64, 67, 72, 75, 76], "n_recurrent_lay": [60, 61, 64, 67, 72, 75, 76, 135], "dropout": [60, 61, 64, 67, 72, 75, 76, 135], "registry_represent": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "input_polici": [60, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "get_policy_in_marl": [60, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "registry_polici": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "gain": [60, 67, 133], "adam": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156], "parameters_actor": [60, 62, 65, 66, 68, 69], "learning_rate_actor": 60, "1e": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156], "5": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 152, 155, 156], "parameters_crit": [60, 62, 65, 66, 68], "learning_rate_crit": 60, "linearlr": [60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 156], "start_factor": [60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 156], "end_factor": [60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 156], "total_it": [60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 156], "act_onehot_shap": 60, "act_shap": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "coma_buffer_rnn": 60, "coma_buff": 60, "input_buff": [60, 61, 64, 67, 72, 75, 76], "obs_shap": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "rew_shap": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "done_shap": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "max_episode_length": [60, 61, 64, 67, 72, 75, 76], "td_lambda": 60, "coma_learn": 60, "on_polici": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "len": [60, 62, 65, 66, 67, 68, 69, 134], "expand": [60, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "batch_ag": [60, 64, 67, 72, 75, 76], "action_prob": 60, "picked_act": 60, "categor": [60, 61, 64, 72, 75, 76, 123], "actions_onehot": 60, "actions_in": 60, "repeat": [60, 71], "agent_mask": [60, 71], "critic_in": [60, 67], "concat": 60, "dim": [60, 71], "values_n": [60, 67], "get_valu": [60, 67], "target": 60, "target_valu": 60, "gather": 60, "long": [60, 105], "update_recurr": [60, 61, 64, 67, 72, 75, 76, 105], "repre_state_dim": 61, "coordination_graph": 61, "dcg_util": 61, "dcg_payoff": 61, "util": [61, 133, 134, 135, 156, 157], "hidden_utility_dim": 61, "payoff": 61, "hidden_payoff_dim": 61, "dcgraph": 61, "graph_typ": 61, "set_coordination_graph": 61, "starcraft2": [61, 84, 136], "dcg_": 61, "hidden_bias_dim": 61, "relu": [61, 83], "learning_r": [61, 64, 67, 71, 72, 73, 75, 76, 83, 156], "marl_offpolicybuffer_rnn": [61, 64, 72, 75, 76], "marl_offpolicybuff": [61, 62, 64, 65, 66, 68, 69, 72, 73, 75, 76], "multi_agent_rl": 61, "dcg_learner": 61, "rnn_hidden_next": 61, "get_hidden_st": [61, 105], "add": [62, 65, 66, 67, 68, 69], "If": [62, 65, 66, 68, 69, 84, 154, 155, 156], "directli": [62, 65, 66, 68, 69, 134, 156], "lr_a": [62, 65, 66, 68, 69], "lr_c": [62, 65, 66, 68, 69], "actions_high": [62, 65, 66, 68, 69], "actions_low": [62, 65, 66, 68, 69], "iddpg_learn": 62, "sigma": [62, 66, 69], "iql_learn": 64, "isac_learn": 65, "rsampl": [65, 68], "maddpg_learn": 66, "representation_crit": 67, "lr": 67, "weight_decai": 67, "marl_onpolicybuffer_rnn": 67, "marl_onpolicybuff": 67, "mappo_clip_learn": 67, "share_valu": 67, "log_pi_a": 67, "length": 67, "squeez": 67, "lr_decai": [67, 105], "masac_learn": 68, "critic_net_a": 69, "critic_net_b": 69, "matd3_learn": 69, "mfac\u7b97\u6cd5\u7684\u5168\u79f0\u662fmean": [], "\u662f\u4e00\u79cd\u57fa\u4e8eactor": [], "critic\u7684\u591a\u667a\u80fd\u4f53\u5f3a\u5316\u5b66\u4e60\u7b97\u6cd5": [], "\u5176\u57fa\u672c\u601d\u60f3\u548cmfq\u7b97\u6cd5\u76f8\u540c": [], "\u5c06\u667a\u80fd\u4f53\u7684\u5c40\u90e8\u89c2\u6d4b": [], "\u5c40\u90e8\u52a8\u4f5c\u548c\u90bb\u5c45\u667a\u80fd\u4f53\u7684\u5e73\u5747\u52a8\u4f5c\u4f5c\u4e3a\u7f51\u8def\u7684\u8f93\u5165": [], "mfac\u91c7\u7528actor": [], "critic\u7ed3\u6784\u5b9e\u73b0\u7b56\u7565\u7684\u66f4\u65b0": [], "\u7f51\u8def\u7ed3\u6784\u548ca2c\u76f8\u4f3c": [], "\u8be5\u7b97\u6cd5\u7684\u7f16\u5199\u53c2\u8003\u5982\u4e0b\u6587\u732e": [], "\u8bba\u6587\u5f15\u7528\u4fe1\u606f": [], "yang2018mean": [], "yang": [], "yaodong": [], "luo": [], "rui": [], "li": [], "minn": [], "zhou": [], "ming": [], "zhang": [], "weinan": [], "wang": [], "jun": [], "intern": 156, "confer": [], "machin": [], "5571": [], "5580": [], "2018": [], "organ": [], "pmlr": [], "act_mean": 71, "variabl": [71, 133, 135, 143, 156], "act_mean_curr": 71, "meanfield_offpolicybuff": 71, "act_prob_shap": 71, "mfq_learner": 71, "q_output": 71, "n_aliv": 71, "action_n_mask": 71, "act_neighbor_sampl": 71, "sample_act": 71, "logit": 71, "act_neighbor_onehot": 71, "qmix_mix": [72, 76], "hidden_dim_mixing_net": [72, 76], "hidden_dim_hyper_net": [72, 76], "qmix_learn": 72, "vdn_mixer": [73, 75], "qtran_bas": 73, "qtran_net": 73, "qtran_net_hidden_dim": 73, "q_hidden_s": [73, 83], "qtran_alt": 73, "valueerror": 73, "recognis": 73, "qtran_mix": 73, "qtran_learn": 73, "greedy_update_step": 73, "can_sampl": 73, "vdac\u7b97\u6cd5\u5168\u79f0\u4e3avalu": [], "vdac\u7b97\u6cd5\u53d1\u626c\u4e86vdn\u7b97\u6cd5\u548ca2c\u7b97\u6cd5\u7684\u4f18\u52bf": [], "\u5c06\u503c\u51fd\u6570\u5206\u89e3\u601d\u60f3\u5f15\u5165actor": [], "critic\u7ed3\u6784\u4e2d": [], "\u5b9e\u73b0\u591a\u667a\u80fd\u4f53\u5206\u5e03\u5f0f\u7b56\u7565\u7684\u4f18\u5316": [], "\u5728\u672c\u7b97\u6cd5\u5e93\u4e2d": [], "vdac\u7684\u7ed3\u6784\u548ca2c\u76f8\u540c": [], "\u4e0d\u540c\u4e4b\u5904\u5728\u4e8evdac\u5c06\u5404\u667a\u80fd\u4f53\u72ec\u7acb\u7684q\u503c\u7ecf\u8fc7vdn": [], "mixer\u5f97\u5230\u6574\u4f53q\u503c": [], "\u8fdb\u800c\u5b9e\u73b0\u7aef\u5230\u7aef\u8bad\u7ec3": [], "\u8be5\u7b97\u6cd5\u7684\u7f16\u5199\u53c2\u8003\u5982\u4e0b\u8bba\u6587": [], "su2021valu": [], "su": [], "jianyu": [], "stephen": [], "bele": [], "proceed": [], "artifici": [], "intellig": [], "35": [], "13": [], "11352": [], "11360": [], "2021": [], "vdn_learner": 75, "alpha": 76, "ff_mixer": 76, "qmix_ff_mix": 76, "hidden_dim_ff_mix_net": 76, "wqmix_learn": 76, "tool": [77, 105, 123, 143, 154], "segment": 77, "tree": 77, "statist": 77, "\u57fa\u7840\u53c2\u6570\u914d\u7f6e\u5b58\u4e8exuanpolici": 83, "basic": [83, 105, 136, 143, 154], "yaml\u6587\u4ef6\u4e2d": 83, "\u793a\u4f8b\u5982\u4e0b": 83, "dl_toolbox": [83, 156], "tensorlay": [83, 156], "xuanpolicy_benchmark": [83, 156], "papers_liu": 83, "parallel": [83, 156], "10": 83, "2910": 83, "2000": 83, "\u9700\u8981\u6ce8\u610f\u7684\u662f": 83, "yaml": [83, 154, 156], "\u6587\u4ef6\u4e2d\u7684": 83, "\u53d8\u91cf\u53d6\u503c\u6839\u636e\u4e0d\u540c\u7684\u6df1\u5ea6\u5b66\u4e60\u6846\u67b6\u6709\u6240\u5dee\u5f02": 83, "\u5206\u522b\u5982\u4e0b": 83, "ascend": 83, "davinci": 83, "\u4ee5dqn\u7b97\u6cd5\u5728atari\u73af\u5883\u4e2d\u7684\u53c2\u6570\u914d\u7f6e\u4e3a\u4f8b": 83, "\u9664\u4e86\u57fa\u7840\u53c2\u6570\u914d\u7f6e\u5916": 83, "\u5176\u7b97\u6cd5\u53c2\u6570\u914d\u7f6e\u5b58\u653e\u4e8e": 83, "\u6587\u4ef6\u4e2d": 83, "\u5185\u5bb9\u5982\u4e0b": 83, "dummy_atari": 83, "al": 83, "breakout": 83, "v5": 83, "obs_typ": 83, "grayscal": 83, "ram": 83, "rgb": 83, "img_siz": 83, "84": 83, "210": 83, "x": [83, 133, 135], "160": 83, "num_stack": 83, "stack": [83, 133, 134], "frame_skip": 83, "skip": 83, "noop_max": 83, "30": 83, "do": 83, "basic_q_network": 83, "basic_cnn": [83, 133], "follow": [83, 84, 154, 155, 156], "three": [83, 156], "argument": [83, 156], "ar": [83, 84, 133, 135, 154, 155, 156, 157], "filter": [83, 133], "32": 83, "64": 83, "16": [83, 156], "kernel": [83, 133], "8": [83, 152, 156], "6": [83, 105, 152], "stride": [83, 133], "512": 83, "activ": [83, 133, 134, 135, 155, 156], "1069": 83, "100000": 83, "0001": 83, "99": [83, 152, 156], "05": [83, 152], "1000000": [83, 156], "1m": 83, "500": 83, "50000000": 83, "50m": 83, "eval_interv": [83, 156], "500000": 83, "\u7531\u4e8eatari\u73af\u5883\u4e2d\u4e00\u5171\u8d85\u8fc760\u4e2a\u4e0d\u540c\u573a\u666f": 83, "\u573a\u666f\u6bd4\u8f83\u7edf\u4e00": 83, "\u53ea\u662f\u4efb\u52a1\u4e0d\u540c": 83, "\u56e0\u6b64\u53ea\u9700\u8981\u4e00\u4e2a\u9ed8\u8ba4\u7684\u53c2\u6570\u914d\u7f6e\u6587\u4ef6\u5373\u53ef": 83, "\u9488\u5bf9\u573a\u666f\u5dee\u5f02\u8f83\u5927\u7684\u73af\u5883": 83, "\u5982": 83, "box2d": [83, 84], "\u73af\u5883\u4e2d\u7684": 83, "carrac": 83, "v2": 83, "\u548c": 83, "lunarland": 83, "\u573a\u666f": 83, "\u524d\u8005\u7684\u72b6\u6001\u8f93\u5165\u662f96": 83, "96": 83, "3\u7684rgb\u56fe\u50cf": 83, "\u540e\u8005\u5219\u662f\u4e00\u4e2a8\u7ef4\u5411\u91cf": 83, "\u56e0\u6b64": 83, "\u9488\u5bf9\u8fd9\u4e24\u4e2a\u573a\u666f\u7684dqn\u7b97\u6cd5\u53c2\u6570\u914d\u7f6e\u5206\u522b\u5b58\u4e8e\u4ee5\u4e0b\u4e24\u4e2a\u6587\u4ef6\u4e2d": 83, "\u7528\u6237\u4e5f\u53ef\u4ee5\u9009\u62e9\u4e0d\u9002\u7528\u7384\u7b56\u63d0\u4f9b\u7684\u9ed8\u8ba4\u53c2\u6570": 83, "\u6216\u8005\u7384\u7b56\u4e2d\u4e0d\u5305\u542b\u7528\u6237\u7684\u4efb\u52a1\u65f6": 83, "\u53ef\u7528\u540c\u6837\u7684\u65b9\u5f0f\u81ea\u5b9a\u4e49": 83, "yaml\u53c2\u6570\u914d\u7f6e\u6587\u4ef6": 83, "\u4f46\u662f\u5728\u83b7\u53d6runner\u7684\u8fc7\u7a0b\u4e2d": 83, "\u9700\u6307\u5b9a\u53c2\u6570\u6587\u4ef6\u7684\u5b58\u653e\u4f4d\u7f6e": 83, "xp": [83, 154], "runner": [83, 154, 156, 157], "get_runn": [83, 154], "method": [83, 133, 134, 135, 154, 156], "classic_control": [83, 154], "cartpol": [83, 154], "v1": [83, 154], "config_path": [83, 156], "xxx": 83, "is_test": [83, 154], "run": [83, 84, 133, 134, 135, 155], "softwar": [84, 135], "singl": [84, 133, 136], "task": [84, 133, 152, 154, 156], "simul": [84, 156], "mujoco": [84, 156, 157], "classic": 84, "under": 84, "It": [84, 155], "also": [84, 133, 134, 135, 154, 155], "mpe": [84, 154, 157], "sisl": 84, "open": [84, 155, 157], "sourc": [84, 155, 156, 157], "pettingzoo": [84, 136], "magent2": [84, 136], "googl": [84, 136], "footbal": [84, 136], "each": [84, 133, 135], "contain": [84, 135, 143, 154, 156], "rich": 84, "varieti": 84, "scenario": [84, 135], "shown": 84, "tabl": 84, "below": 84, "us": [84, 105, 133, 134, 135, 154, 155, 156], "user": [84, 134, 154, 156], "can": [84, 134, 135, 154, 155, 156, 157], "wrap": 84, "specif": [84, 154], "ad": 84, "\u6b65\u9aa4\u4e00": [], "my_env": 84, "make_env": [84, 156], "obeservation_spac": 84, "metadata": 84, "reward_rang": 84, "spec": 84, "mode": 84, "\u6b65\u9aa4\u4e8c": [], "\u5728": [], "py\u6587\u4ef6\u4e2d\u5bfc\u5165\u81ea\u5b9a\u4e49\u7684\u73af\u5883\u7c7bmy_env": [], "myenv": 84, "\u4e3a\u4e86\u63d0\u9ad8\u91c7\u6837\u6548\u7387": [], "\u8282\u7701\u7b97\u6cd5\u8fd0\u884c\u65f6\u95f4": [], "\u672c\u8f6f\u4ef6\u652f\u6301\u5411\u91cf\u5316\u4eff\u771f\u73af\u5883\u8bbe\u7f6e": [], "\u5373\u8fd0\u884c\u591a\u4e2a\u4eff\u771f\u73af\u5883\u540c\u65f6\u91c7\u6837": [], "\u5411\u91cf\u5316\u73af\u5883\u57fa\u7c7bvecenv\u7684\u5b9a\u4e49\u4f4d\u4e8e": [], "py\u6587\u4ef6\u4e2d": [], "\u5728\u6b64\u57fa\u7c7b\u4e0a\u5b9a\u4e49\u7ee7\u627f\u7c7bdummyvecenv\u53cadummyvecenv_ma": [], "\u5206\u522b\u7528\u4e8e\u5b9e\u73b0\u5355\u667a\u80fd\u4f53\u548c\u591a\u667a\u80fd\u4f53\u5411\u91cf\u5316\u4eff\u771f\u73af\u5883": [], "\u4ee3\u7801\u4f4d\u4e8e": [], "dummy_vec_env": 84, "paramt": 105, "argpars": [105, 156], "iter": 105, "state_dict": 105, "file_nam": 105, "listdir": 105, "chang": [105, 155], "break": 105, "remov": 105, "sort": 105, "load_state_dict": 105, "map_loc": 105, "7": [105, 152, 155], "value_norm": 105, "set_devic": 105, "gpu_id": 105, "actions_int": 105, "num_act": 105, "one_hot": 105, "num_class": 105, "system": 123, "either": 123, "discrtet": 123, "contin": 123, "mixier": 123, "algorithm": [84, 123, 133, 143, 154, 156], "mlp": [132, 133, 135, 143], "layer": [132, 133, 134, 135, 143], "perceptron": [132, 134], "cnn": [132, 143], "convolut": [132, 133], "neural": [132, 133, 134, 135], "\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u4e3b\u8981\u7528\u4e8e\u5904\u7406\u56fe\u50cf\u8f93\u5165\u6570\u636e": [], "\u63d0\u53d6\u51fa\u7279\u5f81\u5411\u91cf": [], "\u4e00\u822c\u8f93\u5165\u7c7b\u578b\u4e3a\u591a\u901a\u9053\u56fe\u50cf\u77e9\u9635": [], "\u8f93\u51fa\u591a\u7ef4\u5411\u91cf": [], "\u540d\u79f0\u4e3a": [], "cnn_block": 133, "\u5176\u5b9a\u4e49\u4f4d\u4e8e": [], "xuance_torch": [], "py\u548c": [], "xuance_m": [], "py\u4e2d": [], "\u5b9e\u4f8b\u5316\u8be5\u7c7b\u9700\u8981\u6307\u5b9a\u8f93\u5165\u5c3a\u5bf8": [], "input_shap": [133, 134, 135, 156], "\u6ee4\u6ce2\u65b9\u6cd5": [], "\u6838\u5927\u5c0f": [], "kernel_s": 133, "\u6b65\u957f": [], "\u5f52\u4e00\u5316\u65b9\u6cd5": [], "\u6fc0\u6d3b\u51fd\u6570": [], "\u521d\u59cb\u5316\u65b9\u6cd5": [], "initi": [133, 134, 135, 156], "\u5728pytorch\u4e0b\u5b9e\u73b0\u8fd8\u9700\u6307\u5b9a\u8bbe\u5907\u7c7b\u578b": [], "\u4ee5\u786e\u5b9a\u6a21\u578b\u5728cpu\u4e0a\u8fd0\u884c\u8fd8\u662fgpu": [], "convolv": 133, "two": [84, 133, 135, 154, 155], "produc": 133, "_create_network": [133, 134, 135], "netowrk": [133, 134, 135], "forward": [133, 134, 135], "featur": [133, 134, 135], "ac_cnn_atari": 133, "fc_hidden_s": [133, 135], "final": [133, 154, 156], "fulli": [133, 135], "connect": [133, 135], "_init_lay": 133, "sqrt": 133, "bia": 133, "bias": 133, "sing": 133, "orthogon": 133, "initil": 133, "defualt": 133, "moduletyp": [133, 134, 135], "callabl": [133, 134, 135], "zip": 133, "extend": [133, 134, 135], "adaptivemaxpool2d": 133, "flatten": 133, "sequenti": [133, 134, 135], "255": 133, "tensor_observ": [133, 134], "orthogonal_": [133, 156], "constant_": 133, "prod": 133, "h": [133, 134, 135], "mlp_block": [133, 134, 135], "\u591a\u5c42\u611f\u77e5\u5668\u662f\u4e00\u79cd\u6700\u7b80\u5355\u7684\u6df1\u5c42\u795e\u7ecf\u7f51\u7edc\u6a21\u578b": [], "\u7528\u4e8e\u5904\u7406\u5411\u91cf\u8f93\u5165": [], "\u7528\u6237\u53ef\u6839\u636e\u5404\u81ea\u9700\u8981\u5b9e\u4f8b\u5316\u591a\u5c42\u611f\u77e5\u5668\u6a21\u5757": [], "\u7c7b\u540d\u79f0\u4e3amlp_block": [], "\u5b9e\u4f8b\u5316\u8be5\u7c7b\u9700\u6307\u5b9a\u8f93\u5165\u7ef4\u5ea6\u5927\u5c0f": [], "input_dim": [134, 135], "\u8f93\u51fa\u7ef4\u5ea6\u5927\u5c0f": [], "output_dim": [134, 135], "\u6fc0\u6d3b\u51fd\u6570\u9009\u62e9": [], "basic_ident": 134, "basic_mlp": [134, 156], "assert": 134, "hidden_s": [134, 135, 156], "\u5faa\u73af\u795e\u7ecf\u7f51\u7edc\u4e3b\u8981\u7528\u4e8e\u5904\u7406\u65f6\u5e8f\u4fe1\u53f7\u4fe1\u606f": [], "\u63d0\u53d6\u51fa\u5f53\u524d\u65f6\u5e8f\u4fe1\u53f7\u7684\u7279\u5f81\u5411\u91cf": [], "\u6839\u636e\u4f7f\u7528\u573a\u666f\u5dee\u5f02": [], "\u672c\u8f6f\u4ef6\u63d0\u4f9b\u4e24\u79cd\u5faa\u73af\u795e\u7ecf\u7f51\u8def\u6a21\u5757": [], "gru_block\u548clstm_block": [], "\u5176\u5b9a\u4e49\u5747\u4f4d\u4e8e": [], "\u526a\u679d\u65b9\u6cd5": [], "droupout": [], "\u540c\u6837\u5730": [], "basic_rnn": 135, "which": [84, 134, 135, 154, 156], "befor": [135, 155], "recurrent_hidden_s": 135, "c": 135, "last": 135, "lstm": 135, "init_hidden": 135, "batch": 135, "init_hidden_item": 135, "slice": 135, "given": 135, "get_hidden_item": 135, "use_norm": 135, "input_norm": 135, "norm_rnn": 135, "mlp_layer": 135, "rnn_layer": 135, "lstm_block": 135, "gru_block": 135, "mlp_output": 135, "flatten_paramet": 135, "hn": 135, "cn": 135, "rnn_cell": 135, "cell_stat": 135, "zeros_lik": 135, "runner_bas": 136, "set": [84, 136, 156], "runner_drl": 136, "runner_pettingzoo": 136, "runner_sc2": 136, "runner_footbal": 136, "runner_mag": 136, "reform": 143, "block": [133, 143], "oper": [143, 156], "some": [143, 155, 156], "norm": 143, "ant": [152, 156], "halfcheetah": 152, "hopper": 152, "walker2d": 152, "swimmer": 152, "humanoid": 152, "reacher": 152, "ipendulum": 152, "idpendulum": 152, "1472": 152, "10093": 152, "3434": 152, "9": 152, "2443": 152, "67": 152, "9359": 152, "tianshou": 152, "990": 152, "11718": 152, "2197": 152, "1400": 152, "144": 152, "177": 152, "8364": 152, "1005": 152, "3305": 152, "2020": 152, "1843": 152, "9355": 152, "spinningup": 152, "840": 152, "11000": 152, "1800": 152, "1950": 152, "137": 152, "4822": 152, "10718": 152, "3492": 152, "4307": 152, "59": 152, "547": 152, "88": 152, "07": 152, "9358": 152, "5116": 152, "10201": 152, "3472": 152, "3982": 152, "104": 152, "5189": 152, "9349": 152, "4372": 152, "9637": 152, "3564": 152, "4682": 152, "9337": 152, "3800": 152, "9750": 152, "2860": 152, "4000": 152, "78": 152, "1420": 152, "2674": 152, "825": 152, "970": 152, "51": 152, "240": 152, "11": 152, "9357": 152, "3485": 152, "1829": 152, "1253": 152, "1091": 152, "36": 152, "1726": 152, "9257": 152, "900": 152, "850": 152, "31": 152, "24": 152, "8100": 152, "2810": 152, "4628": 152, "3450": 152, "4318": 152, "108": 152, "705": 152, "3258": 152, "5783": 152, "2609": 152, "3588": 152, "66": 152, "787": 152, "9231": 152, "2330": 152, "3460": 152, "8000": 152, "650": 152, "1670": 152, "1850": 152, "1230": 152, "120": 152, "In": [154, 156], "easi": [154, 155, 157], "first": [154, 156], "need": [133, 134, 135, 154], "built": 154, "toi": 157, "v0": 154, "after": [154, 155, 156], "code": [84, 154, 155, 156], "support": [84, 154], "both": 154, "cooper": 154, "competit": 154, "similali": 154, "simple_spread": [], "For": 154, "competitv": 154, "divid": [154, 156], "more": 154, "side": 154, "demo": 154, "simple_push": 154, "thi": [84, 133, 134, 135, 154, 155, 156, 157], "adversary_0": 154, "agent_0": 154, "adversari": 154, "runner_test": [], "what": [], "happen": [], "automat": [], "gener": [], "result": [154, 156], "abl": [], "see": [], "command": [154, 155, 156], "librari": 155, "linux": 155, "window": 155, "maco": 155, "eulero": 155, "anaconda": 155, "prepar": [155, 156], "python": [155, 156], "conda": 155, "suggest": 155, "xpolici": 155, "pip": 155, "doe": 155, "includ": [155, 156], "depend": [135, 154, 155], "toolbox": [155, 156, 157], "tensorflow2": 155, "all": [155, 156], "extra": 155, "packag": [155, 156], "manual": 155, "further": [155, 156], "usag": [135, 155, 157], "help": 156, "instal": 157, "tutori": 156, "take": [133, 154, 156], "exampl": [], "necessari": 156, "here": 156, "we": [156, 157], "show": 156, "dqn_cartpol": [], "an": [156, 157], "ensembl": 157, "call": [156, 157], "xuan": 157, "ce": 157, "\u7384\u7b56": 157, "chines": 157, "\u7384": 157, "incred": 157, "magic": 157, "\u7b56": 157, "sensit": 157, "tune": 157, "vari": 157, "perform": [154, 156, 157], "differ": 157, "suffer": 157, "unstabl": 157, "therefor": 157, "sometim": 157, "seem": 157, "elus": 157, "give": 157, "thorough": 157, "qualiti": 157, "understand": [156, 157], "hope": 157, "hint": 157, "expect": 157, "compat": 157, "multipl": [84, 157], "realli": 157, "becom": 157, "zoo": 157, "THe": 157, "ha": [155, 157], "been": [155, 157], "github": [154, 156, 157], "openi": 157, "http": [154, 155, 156, 157], "com": [154, 155, 156, 157], "agi": [155, 156, 157], "brain": [155, 156, 157], "git": [154, 155, 157], "quick": 157, "profession": 157, "magent": 157, "search": [156, 157], "simple_spread_v3": 154, "simple_push_v3": 154, "complet": 154, "design": 154, "abov": [154, 155, 156], "benchmark": [154, 156], "instead": 154, "obtain": [154, 156], "folder": [84, 154], "root": 154, "actual": 154, "configur": [154, 156], "w": 154, "b": 154, "account": 154, "offici": 154, "instruct": [154, 156], "usernam": 154, "its": [154, 155], "local": 154, "deploy": 154, "refer": 154, "server": 154, "wai": 155, "them": 155, "altern": 155, "same": 155, "download": 155, "clone": 155, "cd": 155, "xuanc": [], "enter": 155, "runtim": 155, "Then": [155, 156], "error": 155, "warn": 155, "messag": 155, "displai": 155, "indic": 155, "successfulli": 155, "proce": 155, "previou": 156, "demonstr": 156, "how": 156, "order": 156, "better": 156, "facilit": 156, "develop": 156, "own": [134, 156], "section": 156, "detail": 156, "introduct": 156, "api": 156, "bottom": 156, "your_user_nam": 156, "dummy_gym": 156, "representation_hidden_s": 156, "256": 156, "actor_hidden_s": 156, "critic_hidden_s": 156, "leakyrelu": 156, "79811": 156, "0004": 156, "25": 156, "001": 156, "95": 156, "5000": 156, "mainli": [133, 135, 156], "read": 156, "creation": 156, "ppo_mujoco": 156, "py": [84, 133, 134, 135, 156], "write": 156, "consol": 156, "parse_arg": 156, "line": 156, "parser": 156, "argumentpars": 156, "add_argu": 156, "invertedpendulum": 156, "v4": 156, "ppo_mujoco_config": 156, "get_argu": 156, "__name__": 156, "__main__": 156, "parser_arg": 156, "readabl": 156, "combin": 156, "alreadi": 156, "thei": [84, 133, 156], "pars": [], "r": [], "duplic": 156, "latter": 156, "overwrit": 156, "former": 156, "ultim": 156, "instanti": [133, 134, 135, 156], "definit": [84, 135, 156], "comment": 156, "deepcopi": 156, "set_se": 156, "activationfunct": 156, "gaussian_ac_polici": 156, "ppoclip_ag": 156, "args_test": 156, "epoch": 156, "num_epoch": 156, "test_scor": 156, "best_scores_info": 156, "averag": 156, "standard": 156, "deviat": 156, "i_epoch": 156, "begin": 156, "than": 156, "histori": 156, "best_model": 156, "pth": 156, "without": 156, "n_train_step": 156, "final_train_model": 156, "python_mujoco": 156, "visit": 156, "extract": [133, 135], "usual": 133, "matric": 133, "dimension": 133, "defin": [133, 134], "when": [133, 134, 135], "determin": [133, 134, 135], "whether": [133, 134, 135], "one": 134, "simplest": 134, "dimens": [134, 135], "signal": 135, "Their": 135, "found": [84, 135], "respect": [84, 135], "prune": 135, "similarli": 135, "raw": [], "html": [], "br": [], "hr": [], "navig": 84, "improv": 84, "effici": 84, "up": 84, "involv": 84, "simultan": 84, "On": 84, "top": 84, "dummyvecenv": 84}, "objects": {"xuanpolicy.mindspore.agents.agents_marl": [[59, 0, 1, "", "MARLAgent"]], "xuanpolicy.mindsporetensorflow.agent.agent": [[40, 0, 1, "", "Agent"]], "xuanpolicy.tensorflow.agents.agents_marl": [[59, 0, 1, "", "MARLAgent"]], "xuanpolicy.tensorflowtensorflow.agent.agent": [[40, 0, 1, "", "Agent"]], "xuanpolicy.torch.agent.mutli_agent_rl.coma_agents": [[60, 0, 1, "", "COMA_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.coma_agents.COMA_Agents": [[60, 1, 1, "", "act"], [60, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.dcg_agents": [[61, 0, 1, "", "DCG_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.dcg_agents.DCG_Agents": [[61, 1, 1, "", "act"], [61, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.iddpg_agents": [[62, 0, 1, "", "IDDPG_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.iddpg_agents.IDDPG_Agents": [[62, 1, 1, "", "act"], [62, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.ippo_agents": [[63, 0, 1, "", "IPPO_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.iql_agents": [[64, 0, 1, "", "IQL_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.iql_agents.IQL_Agents": [[64, 1, 1, "", "act"], [64, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.isac_agents": [[65, 0, 1, "", "ISAC_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.isac_agents.ISAC_Agents": [[65, 1, 1, "", "act"], [65, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.maddpg_agents": [[66, 0, 1, "", "MADDPG_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.maddpg_agents.MADDPG_Agents": [[66, 1, 1, "", "act"], [66, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.mappo_agents": [[67, 0, 1, "", "MAPPO_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.mappo_agents.MAPPO_Agents": [[67, 1, 1, "", "act"], [67, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.masac_agents": [[68, 0, 1, "", "MASAC_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.masac_agents.MASAC_Agents": [[68, 1, 1, "", "act"], [68, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.matd3_agents": [[69, 0, 1, "", "MATD3_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.matd3_agents.MATD3_Agents": [[69, 1, 1, "", "act"], [69, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.mfq_agents": [[71, 0, 1, "", "MFQ_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.mfq_agents.MFQ_Agents": [[71, 1, 1, "", "act"], [71, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.qmix_agents": [[72, 0, 1, "", "QMIX_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.qmix_agents.QMIX_Agents": [[72, 1, 1, "", "act"], [72, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.qtran_agents": [[73, 0, 1, "", "QTRAN_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.qtran_agents.QTRAN_Agents": [[73, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.vdn_agents": [[75, 0, 1, "", "VDN_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.vdn_agents.VDN_Agents": [[75, 1, 1, "", "act"], [75, 1, 1, "", "train"]], "xuanpolicy.torch.agent.mutli_agent_rl.wqmix_agents": [[76, 0, 1, "", "WQMIX_Agents"]], "xuanpolicy.torch.agent.mutli_agent_rl.wqmix_agents.WQMIX_Agents": [[76, 1, 1, "", "act"], [76, 1, 1, "", "train"]], "xuanpolicy.torch.agent.policy_gradient.a2c_agent": [[39, 0, 1, "", "A2C_Agent"]], "xuanpolicy.torch.agent.policy_gradient.a2c_agent.A2C_Agent": [[39, 1, 1, "", "_action"], [39, 1, 1, "", "test"], [39, 1, 1, "", "train"]], "xuanpolicy.torch.agent.policy_gradient.ddpg_agent": [[42, 0, 1, "", "DDPG_Agent"]], "xuanpolicy.torch.agent.policy_gradient.ddpg_agent.DDPG_Agent": [[42, 1, 1, "", "_action"], [42, 1, 1, "", "test"], [42, 1, 1, "", "train"]], "xuanpolicy.torch.agent.policy_gradient.mpdqn_agent": [[46, 0, 1, "", "MPDQN_Agent"]], "xuanpolicy.torch.agent.policy_gradient.mpdqn_agent.MPDQN_Agent": [[46, 1, 1, "", "_action"], [46, 1, 1, "", "pad_action"], [46, 1, 1, "", "test"], [46, 1, 1, "", "train"]], "xuanpolicy.torch.agent.policy_gradient.pdqn_agent": [[48, 0, 1, "", "PDQN_Agent"]], "xuanpolicy.torch.agent.policy_gradient.pdqn_agent.PDQN_Agent": [[48, 1, 1, "", "_action"], [48, 1, 1, "", "pad_action"], [48, 1, 1, "", "test"], [48, 1, 1, "", "train"]], "xuanpolicy.torch.agent.policy_gradient.pg_agent": [[50, 0, 1, "", "PG_Agent"]], "xuanpolicy.torch.agent.policy_gradient.pg_agent.PG_Agent": [[50, 1, 1, "", "_action"], [50, 1, 1, "", "test"], [50, 1, 1, "", "train"]], "xuanpolicy.torch.agent.policy_gradient.ppg_agent": [[51, 0, 1, "", "PPG_Agent"]], "xuanpolicy.torch.agent.policy_gradient.ppg_agent.PPG_Agent": [[51, 1, 1, "", "_action"], [51, 1, 1, "", "test"], [51, 1, 1, "", "train"]], "xuanpolicy.torch.agent.policy_gradient.ppoclip_agent": [[52, 0, 1, "", "PPOCLIP_Agent"]], "xuanpolicy.torch.agent.policy_gradient.ppoclip_agent.PPOCLIP_Agent": [[52, 1, 1, "", "_action"], [52, 1, 1, "", "test"], [52, 1, 1, "", "train"]], "xuanpolicy.torch.agent.policy_gradient.ppokl_agent": [[53, 0, 1, "", "PPOKL_Agent"]], "xuanpolicy.torch.agent.policy_gradient.ppokl_agent.PPOKL_Agent": [[53, 1, 1, "", "_action"], [53, 1, 1, "", "test"], [53, 1, 1, "", "train"]], "xuanpolicy.torch.agent.policy_gradient.sac_agent": [[55, 0, 1, "", "SAC_Agent"]], "xuanpolicy.torch.agent.policy_gradient.sac_agent.SAC_Agent": [[55, 1, 1, "", "_action"], [55, 1, 1, "", "test"], [55, 1, 1, "", "train"]], "xuanpolicy.torch.agent.policy_gradient.sacdis_agent": [[56, 0, 1, "", "SACDIS_Agent"]], "xuanpolicy.torch.agent.policy_gradient.sacdis_agent.SACDIS_Agent": [[56, 1, 1, "", "_action"], [56, 1, 1, "", "test"], [56, 1, 1, "", "train"]], "xuanpolicy.torch.agent.policy_gradient.spdqn_agent": [[57, 0, 1, "", "SPDQN_Agent"]], "xuanpolicy.torch.agent.policy_gradient.spdqn_agent.SPDQN_Agent": [[57, 1, 1, "", "_action"], [57, 1, 1, "", "pad_action"], [57, 1, 1, "", "test"], [57, 1, 1, "", "train"]], "xuanpolicy.torch.agent.policy_gradient.td3_agent": [[58, 0, 1, "", "TD3_Agent"]], "xuanpolicy.torch.agent.policy_gradient.td3_agent.TD3_Agent": [[58, 1, 1, "", "_action"], [58, 1, 1, "", "test"], [58, 1, 1, "", "train"]], "xuanpolicy.torch.agent.qlearning_family.c51_agent": [[41, 0, 1, "", "C51_Agent"]], "xuanpolicy.torch.agent.qlearning_family.c51_agent.C51_Agent": [[41, 1, 1, "", "_action"], [41, 1, 1, "", "test"], [41, 1, 1, "", "train"]], "xuanpolicy.torch.agent.qlearning_family.ddqn_agent": [[43, 0, 1, "", "DDQN_Agent"]], "xuanpolicy.torch.agent.qlearning_family.ddqn_agent.DDQN_Agent": [[43, 1, 1, "", "_action"], [43, 1, 1, "", "test"], [43, 1, 1, "", "train"]], "xuanpolicy.torch.agent.qlearning_family.dqn_agent": [[44, 0, 1, "", "DQN_Agent"]], "xuanpolicy.torch.agent.qlearning_family.dqn_agent.DQN_Agent": [[44, 1, 1, "", "_action"], [44, 1, 1, "", "test"], [44, 1, 1, "", "train"]], "xuanpolicy.torch.agent.qlearning_family.dueldqn_agent": [[45, 0, 1, "", "DuelDQN_Agent"]], "xuanpolicy.torch.agent.qlearning_family.dueldqn_agent.DuelDQN_Agent": [[45, 1, 1, "", "_action"], [45, 1, 1, "", "test"], [45, 1, 1, "", "train"]], "xuanpolicy.torch.agent.qlearning_family.noisydqn_agent": [[47, 0, 1, "", "NoisyDQN_Agent"]], "xuanpolicy.torch.agent.qlearning_family.noisydqn_agent.NoisyDQN_Agent": [[47, 1, 1, "", "_action"], [47, 1, 1, "", "test"], [47, 1, 1, "", "train"]], "xuanpolicy.torch.agent.qlearning_family.perdqn_agent": [[49, 0, 1, "", "PerDQN_Agent"]], "xuanpolicy.torch.agent.qlearning_family.perdqn_agent.PerDQN_Agent": [[49, 1, 1, "", "_action"], [49, 1, 1, "", "test"], [49, 1, 1, "", "train"]], "xuanpolicy.torch.agent.qlearning_family.qrdqn_agent": [[54, 0, 1, "", "QRDQN_Agent"]], "xuanpolicy.torch.agent.qlearning_family.qrdqn_agent.QRDQN_Agent": [[54, 1, 1, "", "_action"], [54, 1, 1, "", "test"], [54, 1, 1, "", "train"]], "xuanpolicy.torch.agents.agent": [[40, 0, 1, "", "Agent"]], "xuanpolicy.torch.agents.agent.Agent": [[40, 1, 1, "", "_action"], [40, 1, 1, "", "_process_observation"], [40, 1, 1, "", "_process_reward"], [40, 1, 1, "", "finish"], [40, 1, 1, "", "load_model"], [40, 1, 1, "", "log_infos"], [40, 1, 1, "", "log_videos"], [40, 1, 1, "", "save_model"], [40, 1, 1, "", "test"], [40, 1, 1, "", "train"]], "xuanpolicy.torch.agents.agents_marl": [[59, 0, 1, "", "MARLAgent"], [59, 0, 1, "", "RandomAgents"], [59, 0, 1, "", "linear_decay_or_increase"]], "xuanpolicy.torch.agents.agents_marl.MARLAgent": [[59, 1, 1, "", "act"], [59, 1, 1, "", "load_model"], [59, 1, 1, "", "save_model"], [59, 1, 1, "", "train"]], "xuanpolicy.torch.agents.agents_marl.RandomAgents": [[59, 1, 1, "", "act"]], "xuanpolicy.torch.agents.agents_marl.linear_decay_or_increase": [[59, 1, 1, "", "update"]], "xuanpolicy.torch.learners.learner": [[105, 0, 1, "", "Learner"]], "xuanpolicy.torch.learners.learner.Learner": [[105, 1, 1, "", "load_model"], [105, 1, 1, "", "save_model"], [105, 1, 1, "", "update"]], "xuanpolicy.torch.representations.cnn": [[133, 0, 1, "", "AC_CNN_Atari"], [133, 0, 1, "", "Basic_CNN"]], "xuanpolicy.torch.representations.cnn.AC_CNN_Atari": [[133, 1, 1, "", "_create_network"], [133, 1, 1, "", "_init_layer"], [133, 1, 1, "", "forward"]], "xuanpolicy.torch.representations.cnn.Basic_CNN": [[133, 1, 1, "", "_create_network"], [133, 1, 1, "", "forward"]], "xuanpolicy.torch.representations.mlp": [[134, 0, 1, "", "Basic_Identical"], [134, 0, 1, "", "Basic_MLP"]], "xuanpolicy.torch.representations.mlp.Basic_Identical": [[134, 1, 1, "", "forward"]], "xuanpolicy.torch.representations.mlp.Basic_MLP": [[134, 1, 1, "", "_create_network"], [134, 1, 1, "", "forward"]], "xuanpolicy.torch.representations.rnn": [[135, 0, 1, "", "Basic_RNN"]], "xuanpolicy.torch.representations.rnn.Basic_RNN": [[135, 1, 1, "", "_create_network"], [135, 1, 1, "", "forward"], [135, 1, 1, "", "get_hidden_item"], [135, 1, 1, "", "init_hidden"], [135, 1, 1, "", "init_hidden_item"]]}, "objtypes": {"0": "py:class", "1": "py:function"}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"]}, "titleterms": {"a2c": 0, "advantag": 0, "actor": [0, 14, 15], "critic": [0, 14, 15], "c51": 1, "ddpg": 2, "deep": [2, 3, 19], "determinist": [2, 127, 128], "polici": [2, 12, 18, 123], "gradient": [2, 18], "ddqn": 3, "doubl": 3, "q": [3, 25], "network": [3, 36, 146], "dqn": [4, 6, 8, 10], "algorithm": [4, 5, 19, 20, 157], "descript": [4, 5], "drqn": 5, "duel": 6, "mpdqn": 7, "noisi": 8, "pdqn": 9, "per": 10, "ppg": 11, "ppo": 12, "proxim": 12, "optim": 12, "qrdqn": 13, "soft": [14, 15], "spdqn": 16, "td3": 17, "vanilla": 18, "reinforc": [19, 20], "learn": [19, 20, 25], "includ": 84, "multi": 20, "agent": [20, 38, 40], "coma": 21, "dcg": 22, "iddpg": 23, "iql": 25, "independ": 25, "isac": 26, "maddpg": 27, "mappo": 28, "masac": 29, "matd3": 30, "mfac": [31, 70], "mfq": 32, "qmix": [33, 37], "qtran": 34, "vdac": [35, 74], "vdn": 36, "valu": 36, "decomposit": 36, "weight": 37, "a2c_ag": 39, "\u6e90\u7801": [], "c51_agent": 41, "ddpg_agent": 42, "ddqn_agent": 43, "dqn_agent": 44, "dueldqn_ag": 45, "mpdqn_agent": 46, "noisydqn_ag": 47, "pdqn_agent": 48, "perdqn_ag": 49, "pg_agent": 50, "ppg_agent": 51, "ppoclip_ag": 52, "ppokl_ag": 53, "qrdqn_agent": 54, "sac_ag": 55, "sacdis_ag": 56, "spdqn_agent": 57, "td3_agent": 58, "marlag": 59, "coma_ag": 60, "dcg_agent": 61, "iddpg_ag": 62, "ippo_ag": 63, "iql_ag": 64, "isac_ag": 65, "maddpg_ag": 66, "mappo_ag": 67, "masac_ag": 68, "matd3_ag": 69, "\u7b97\u6cd5\u63cf\u8ff0": [], "\u7b97\u6cd5\u51fa\u5904": [], "mfq_agent": 71, "qmix_ag": 72, "qtran_ag": 73, "vdn_agent": 75, "wqmix_ag": 76, "common": [77, 78], "tool": [78, 82], "memori": [79, 80], "marl": [20, 80, 125, 128, 130, 154], "segment": 81, "tree": 81, "statist": 82, "config": [83, 156], "\u57fa\u7840\u53c2\u6570\u914d\u7f6e": 83, "\u7b97\u6cd5\u53c2\u6570\u914d\u7f6e": 83, "\u81ea\u5b9a\u4e49\u53c2\u6570\u914d\u7f6e": 83, "environ": [84, 149, 150, 151, 153], "custom": 84, "\u5411\u91cf\u5316\u4eff\u771f\u73af\u5883": [], "learner": [85, 105], "a2c_learn": 86, "c51_learner": 87, "ddpg_learner": 88, "ddqn_learner": 89, "dqn_learner": 90, "dueldqn_learn": 91, "mpdqn_learner": 92, "noisydqn_learn": 93, "pdqn_learner": 94, "perdqn_learn": 95, "pg_learner": 96, "ppg_learner": 97, "ppoclip_learn": 98, "ppokl_learn": 99, "qrdqn_learner": 100, "sac_learn": 101, "sacdis_learn": 102, "spdqn_learner": 103, "td3_learner": 104, "coma_learn": 106, "dcg_learner": 107, "iddpg_learn": 108, "ippo_learn": 109, "iql_learn": 110, "isac_learn": 111, "maddpg_learn": 112, "mappo_learn": 113, "masac_learn": 114, "matd3_learn": 115, "mfac_learn": 116, "mfq_learner": 117, "qmix_learn": 118, "qtran_learn": 119, "vdac_learn": 120, "vdn_learner": 121, "wqmix_learn": 122, "categor": [124, 125], "coordin": 126, "graph": 126, "gaussian": [129, 130], "mixier": 131, "represent": 132, "cnn": 133, "base": [133, 134, 135], "mlp": 134, "rnn": 135, "runner": 136, "runner_bas": 137, "runner_drl": 138, "runner_footbal": 139, "runner_mag": 140, "runner_pettingzoo": 141, "runner_sc2": 142, "util": 143, "distribut": 144, "input": 145, "reform": 145, "neural": 146, "layer": 146, "oper": 147, "valuenorm": 148, "atari": 149, "benchmark": [149, 150, 151, 152, 153, 157], "\u73af\u5883\u4ecb\u7ecd": [], "magent": 150, "mpe": 151, "mujoco": 152, "scenario": 152, "result": 152, "toi": 153, "quick": 154, "start": 154, "run": [154, 156], "drl": [19, 154], "an": 154, "test": [154, 155], "logger": 154, "instal": 155, "profession": 156, "usag": 156, "step": 156, "1": 156, "creat": 156, "file": 156, "2": 156, "build": [], "3": 156, "4": [], "5": [], "select": [], "6": [], "7": [], "8": [], "train": [], "model": 156, "9": [], "10": [], "visual": [], "infom": [], "welcom": 157, "xuanpolici": 157, "": 157, "document": 157, "how": 157, "us": 157, "api": 157, "indic": 157, "tabl": 157, "exampl": [154, 156], "via": 155, "pypi": 155, "from": 155, "github": 155, "repositori": 155, "whether": 155, "wa": 155, "success": 155, "method": [], "get": 156, "attribut": 156, "defin": 156, "sourc": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 133, 134, 135], "code": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 133, 134, 135], "discret": 15, "action": 15, "space": 15, "ippo": 24, "vector": 84}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"A2C: Advantage Actor-Critic": [[0, "a2c-advantage-actor-critic"]], "C51": [[1, "c51"]], "DDPG: Deep Deterministic Policy Gradient": [[2, "ddpg-deep-deterministic-policy-gradient"]], "DDQN: Double Deep Q-Networks": [[3, "ddqn-double-deep-q-networks"]], "DQN": [[4, "dqn"]], "Algorithm description": [[4, "algorithm-description"], [5, "algorithm-description"]], "DRQN": [[5, "drqn"]], "Duel DQN": [[6, "duel-dqn"]], "MPDQN": [[7, "mpdqn"]], "Noisy DQN": [[8, "noisy-dqn"]], "PDQN": [[9, "pdqn"]], "Per DQN": [[10, "per-dqn"]], "PPG": [[11, "ppg"]], "PPO: Proximal Policy Optimization": [[12, "ppo-proximal-policy-optimization"]], "QRDQN": [[13, "qrdqn"]], "Soft Actor-Critic": [[14, "soft-actor-critic"]], "SPDQN": [[16, "spdqn"]], "TD3": [[17, "td3"]], "Vanilla Policy Gradient": [[18, "vanilla-policy-gradient"]], "COMA": [[21, "coma"]], "DCG": [[22, "dcg"]], "IDDPG": [[23, "iddpg"]], "IQL: Independent Q-Learning": [[25, "iql-independent-q-learning"]], "ISAC": [[26, "isac"]], "MADDPG": [[27, "maddpg"]], "MAPPO": [[28, "mappo"]], "MASAC": [[29, "masac"]], "MATD3": [[30, "matd3"]], "MFAC": [[31, "mfac"], [70, "mfac"]], "MFQ": [[32, "mfq"]], "QMIX": [[33, "qmix"]], "QTRAN": [[34, "qtran"]], "VDAC": [[35, "vdac"], [74, "vdac"]], "VDN: Value Decomposition Networks": [[36, "vdn-value-decomposition-networks"]], "Weighted QMIX": [[37, "weighted-qmix"]], "Agents": [[38, "agents"]], "Common": [[77, "common"]], "Common Tools": [[78, "common-tools"]], "Memory": [[79, "memory"]], "Memory for MARL": [[80, "memory-for-marl"]], "Segment Tree": [[81, "segment-tree"]], "Statistic Tools": [[82, "statistic-tools"]], "Learners": [[85, "learners"]], "Policies": [[123, "policies"]], "Categorical": [[124, "categorical"]], "Categorical-MARL": [[125, "categorical-marl"]], "Coordination-Graph": [[126, "coordination-graph"]], "Deterministic": [[127, "deterministic"]], "Deterministic-MARL": [[128, "deterministic-marl"]], "Gaussian": [[129, "gaussian"]], "Gaussian-MARL": [[130, "gaussian-marl"]], "Mixiers": [[131, "mixiers"]], "Representations": [[132, "representations"]], "Runners": [[136, "runners"]], "Runner_Base": [[137, "runner-base"]], "Runner_DRL": [[138, "runner-drl"]], "Runner_Football": [[139, "runner-football"]], "Runner_MAgent": [[140, "runner-magent"]], "Runner_Pettingzoo": [[141, "runner-pettingzoo"]], "Runner_SC2": [[142, "runner-sc2"]], "Utils": [[143, "utils"]], "Distributions": [[144, "distributions"]], "Input Reformation": [[145, "input-reformation"]], "Neural Network Layers": [[146, "neural-network-layers"]], "Operations": [[147, "operations"]], "ValueNorm": [[148, "valuenorm"]], "MuJoCo benchmarks": [[152, "mujoco-benchmarks"]], "Scenarios": [[152, "scenarios"]], "Results": [[152, "results"]], "Welcome to XuanPolicy\u2019s documentation!": [[157, "welcome-to-xuanpolicy-s-documentation"]], "How to use:": [[157, null]], "API:": [[157, null]], "Benchmarks": [[157, null]], "Algorithms:": [[157, null]], "Indices and tables": [[157, "indices-and-tables"]], "Configs": [[83, "configs"]], "\u57fa\u7840\u53c2\u6570\u914d\u7f6e": [[83, "id1"]], "\u7b97\u6cd5\u53c2\u6570\u914d\u7f6e": [[83, "id2"]], "\u81ea\u5b9a\u4e49\u53c2\u6570\u914d\u7f6e": [[83, "id3"]], "A2C_Agent": [[39, "a2c-agent"]], "Source Code": [[39, "source-code"], [40, "source-code"], [41, "source-code"], [42, "source-code"], [43, "source-code"], [44, "source-code"], [45, "source-code"], [46, "source-code"], [47, "source-code"], [48, "source-code"], [49, "source-code"], [50, "source-code"], [51, "source-code"], [52, "source-code"], [53, "source-code"], [54, "source-code"], [55, "source-code"], [56, "source-code"], [57, "source-code"], [58, "source-code"], [59, "source-code"], [60, "source-code"], [61, "source-code"], [62, "source-code"], [63, "source-code"], [64, "source-code"], [65, "source-code"], [66, "source-code"], [67, "source-code"], [68, "source-code"], [69, "source-code"], [71, "source-code"], [72, "source-code"], [73, "source-code"], [75, "source-code"], [76, "source-code"], [86, "source-code"], [87, "source-code"], [88, "source-code"], [89, "source-code"], [90, "source-code"], [91, "source-code"], [92, "source-code"], [93, "source-code"], [94, "source-code"], [95, "source-code"], [96, "source-code"], [97, "source-code"], [98, "source-code"], [99, "source-code"], [100, "source-code"], [101, "source-code"], [102, "source-code"], [103, "source-code"], [104, "source-code"], [105, "source-code"], [106, "source-code"], [107, "source-code"], [108, "source-code"], [109, "source-code"], [110, "source-code"], [111, "source-code"], [112, "source-code"], [113, "source-code"], [114, "source-code"], [115, "source-code"], [116, "source-code"], [117, "source-code"], [118, "source-code"], [119, "source-code"], [120, "source-code"], [121, "source-code"], [122, "source-code"], [133, "source-code"], [134, "source-code"], [135, "source-code"]], "Agent": [[40, "agent"]], "C51_Agent": [[41, "c51-agent"]], "DDPG_Agent": [[42, "ddpg-agent"]], "DDQN_Agent": [[43, "ddqn-agent"]], "DQN_Agent": [[44, "dqn-agent"]], "DuelDQN_Agent": [[45, "dueldqn-agent"]], "MPDQN_Agent": [[46, "mpdqn-agent"]], "NoisyDQN_Agent": [[47, "noisydqn-agent"]], "PDQN_Agent": [[48, "pdqn-agent"]], "PerDQN_Agent": [[49, "perdqn-agent"]], "PG_Agent": [[50, "pg-agent"]], "PPG_Agent": [[51, "ppg-agent"]], "PPOCLIP_Agent": [[52, "ppoclip-agent"]], "PPOKL_Agent": [[53, "ppokl-agent"]], "QRDQN_Agent": [[54, "qrdqn-agent"]], "SAC_Agent": [[55, "sac-agent"]], "SACDIS_Agent": [[56, "sacdis-agent"]], "SPDQN_Agent": [[57, "spdqn-agent"]], "TD3_Agent": [[58, "td3-agent"]], "MARLAgent": [[59, "marlagent"]], "COMA_Agents": [[60, "coma-agents"]], "DCG_Agents": [[61, "dcg-agents"]], "IDDPG_Agents": [[62, "iddpg-agents"]], "IPPO_Agents": [[63, "ippo-agents"]], "IQL_Agents": [[64, "iql-agents"]], "ISAC_Agents": [[65, "isac-agents"]], "MADDPG_Agents": [[66, "maddpg-agents"]], "MAPPO_Agents": [[67, "mappo-agents"]], "MASAC_Agents": [[68, "masac-agents"]], "MATD3_Agents": [[69, "matd3-agents"]], "MFQ_Agents": [[71, "mfq-agents"]], "QMIX_Agents": [[72, "qmix-agents"]], "QTRAN_Agents": [[73, "qtran-agents"]], "VDN_Agents": [[75, "vdn-agents"]], "WQMIX_Agents": [[76, "wqmix-agents"]], "A2C_Learner": [[86, "a2c-learner"]], "C51_Learner": [[87, "c51-learner"]], "DDPG_Learner": [[88, "ddpg-learner"]], "DDQN_Learner": [[89, "ddqn-learner"]], "DQN_Learner": [[90, "dqn-learner"]], "DuelDQN_Learner": [[91, "dueldqn-learner"]], "MPDQN_Learner": [[92, "mpdqn-learner"]], "NoisyDQN_Learner": [[93, "noisydqn-learner"]], "PDQN_Learner": [[94, "pdqn-learner"]], "PerDQN_Learner": [[95, "perdqn-learner"]], "PG_Learner": [[96, "pg-learner"]], "PPG_Learner": [[97, "ppg-learner"]], "PPOCLIP_Learner": [[98, "ppoclip-learner"]], "PPOKL_Learner": [[99, "ppokl-learner"]], "QRDQN_Learner": [[100, "qrdqn-learner"]], "SAC_Learner": [[101, "sac-learner"]], "SACDIS_Learner": [[102, "sacdis-learner"]], "SPDQN_Learner": [[103, "spdqn-learner"]], "TD3_Learner": [[104, "td3-learner"]], "Learner": [[105, "learner"]], "COMA_Learner": [[106, "coma-learner"]], "DCG_Learner": [[107, "dcg-learner"]], "IDDPG_Learner": [[108, "iddpg-learner"]], "IPPO_Learner": [[109, "ippo-learner"]], "IQL_Learner": [[110, "iql-learner"]], "ISAC_Learner": [[111, "isac-learner"]], "MADDPG_Learner": [[112, "maddpg-learner"]], "MAPPO_Learner": [[113, "mappo-learner"]], "MASAC_Learner": [[114, "masac-learner"]], "MATD3_Learner": [[115, "matd3-learner"]], "MFAC_Learner": [[116, "mfac-learner"]], "MFQ_Learner": [[117, "mfq-learner"]], "QMIX_Learner": [[118, "qmix-learner"]], "QTRAN_Learner": [[119, "qtran-learner"]], "VDAC_Learner": [[120, "vdac-learner"]], "VDN_Learner": [[121, "vdn-learner"]], "WQMIX_Learner": [[122, "wqmix-learner"]], "CNN-based": [[133, "cnn-based"]], "MLP-based": [[134, "mlp-based"]], "Soft Actor-Critic for discrete action space": [[15, "soft-actor-critic-for-discrete-action-space"]], "Deep Reinforcement Learning": [[19, "deep-reinforcement-learning"]], "DRL Algorithms": [[19, null]], "Multi-Agent Reinforcement Learning": [[20, "multi-agent-reinforcement-learning"]], "MARL Algorithms": [[20, null]], "IPPO": [[24, "ippo"]], "Quick Start": [[154, "quick-start"]], "Run a DRL example": [[154, "run-a-drl-example"]], "Run an MARL example": [[154, "run-an-marl-example"]], "Test": [[154, "test"]], "Logger": [[154, "logger"]], "Installation": [[155, "installation"]], "Install via PyPI": [[155, "install-via-pypi"]], "Install from GitHub repository": [[155, "install-from-github-repository"]], "Testing whether the installation was successful": [[155, "testing-whether-the-installation-was-successful"]], "Professional Usage": [[156, "professional-usage"]], "Step 1: Create config file": [[156, "step-1-create-config-file"]], "Step 2: Get the attributes of the example": [[156, "step-2-get-the-attributes-of-the-example"]], "Step 3: Define run(), create and run the model": [[156, "step-3-define-run-create-and-run-the-model"]], "RNN-based": [[135, "rnn-based"]], "Environments": [[84, "environments"], [149, "environments"], [150, "environments"], [151, "environments"], [153, "environments"]], "Included Environments": [[84, "included-environments"]], "Customized Environments": [[84, "customized-environments"]], "Vectorize the Environment": [[84, "vectorize-the-environment"]], "Atari benchmarks": [[149, "atari-benchmarks"]], "Magent benchmarks": [[150, "magent-benchmarks"]], "MPE benchmarks": [[151, "mpe-benchmarks"]], "Toy benchmarks": [[153, "toy-benchmarks"]]}, "indexentries": {}}) \ No newline at end of file +Search.setIndex({"docnames": ["documents/algorithms/drl/a2c", "documents/algorithms/drl/c51", "documents/algorithms/drl/ddpg", "documents/algorithms/drl/ddqn", "documents/algorithms/drl/dqn", "documents/algorithms/drl/drqn", "documents/algorithms/drl/dueldqn", "documents/algorithms/drl/mpdqn", "documents/algorithms/drl/noisydqn", "documents/algorithms/drl/pdqn", "documents/algorithms/drl/perdqn", "documents/algorithms/drl/ppg", "documents/algorithms/drl/ppo", "documents/algorithms/drl/qrdqn", "documents/algorithms/drl/sac", "documents/algorithms/drl/sac_dis", "documents/algorithms/drl/spdqn", "documents/algorithms/drl/td3", "documents/algorithms/drl/vpg", "documents/algorithms/index_drl", "documents/algorithms/index_marl", "documents/algorithms/marl/coma", "documents/algorithms/marl/dcg", "documents/algorithms/marl/iddpg", "documents/algorithms/marl/ippo", "documents/algorithms/marl/iql", "documents/algorithms/marl/isac", "documents/algorithms/marl/maddpg", "documents/algorithms/marl/mappo", "documents/algorithms/marl/masac", "documents/algorithms/marl/matd3", "documents/algorithms/marl/mfac", "documents/algorithms/marl/mfq", "documents/algorithms/marl/qmix", "documents/algorithms/marl/qtran", "documents/algorithms/marl/vdac", "documents/algorithms/marl/vdn", "documents/algorithms/marl/wqmix", "documents/api/agents", "documents/api/agents/drl/a2c", "documents/api/agents/drl/basic_drl_class", "documents/api/agents/drl/c51", "documents/api/agents/drl/ddpg", "documents/api/agents/drl/ddqn", "documents/api/agents/drl/dqn", "documents/api/agents/drl/dueldqn", "documents/api/agents/drl/mpdqn", "documents/api/agents/drl/noisydqn", "documents/api/agents/drl/pdqn", "documents/api/agents/drl/perdqn", "documents/api/agents/drl/pg", "documents/api/agents/drl/ppg", "documents/api/agents/drl/ppo_clip", "documents/api/agents/drl/ppo_kl", "documents/api/agents/drl/qrdqn", "documents/api/agents/drl/sac", "documents/api/agents/drl/sac_dis", "documents/api/agents/drl/spdqn", "documents/api/agents/drl/td3", "documents/api/agents/marl/basic_marl_class", "documents/api/agents/marl/coma", "documents/api/agents/marl/dcg", "documents/api/agents/marl/iddpg", "documents/api/agents/marl/ippo", "documents/api/agents/marl/iql", "documents/api/agents/marl/isac", "documents/api/agents/marl/maddpg", "documents/api/agents/marl/mappo", "documents/api/agents/marl/masac", "documents/api/agents/marl/matd3", "documents/api/agents/marl/mfac", "documents/api/agents/marl/mfq", "documents/api/agents/marl/qmix", "documents/api/agents/marl/qtran", "documents/api/agents/marl/vdac", "documents/api/agents/marl/vdn", "documents/api/agents/marl/wqmix", "documents/api/common", "documents/api/common/common_tools", "documents/api/common/memory_tools", "documents/api/common/memory_tools_marl", "documents/api/common/segtree_tool", "documents/api/common/statistic_tools", "documents/api/configs", "documents/api/environments", "documents/api/learners", "documents/api/learners/drl/a2c", "documents/api/learners/drl/c51", "documents/api/learners/drl/ddpg", "documents/api/learners/drl/ddqn", "documents/api/learners/drl/dqn", "documents/api/learners/drl/dueldqn", "documents/api/learners/drl/mpdqn", "documents/api/learners/drl/noisydqn", "documents/api/learners/drl/pdqn", "documents/api/learners/drl/perdqn", "documents/api/learners/drl/pg", "documents/api/learners/drl/ppg", "documents/api/learners/drl/ppo_clip", "documents/api/learners/drl/ppo_kl", "documents/api/learners/drl/qrdqn", "documents/api/learners/drl/sac", "documents/api/learners/drl/sac_dis", "documents/api/learners/drl/spdqn", "documents/api/learners/drl/td3", "documents/api/learners/learner", "documents/api/learners/marl/coma", "documents/api/learners/marl/dcg", "documents/api/learners/marl/iddpg", "documents/api/learners/marl/ippo", "documents/api/learners/marl/iql", "documents/api/learners/marl/isac", "documents/api/learners/marl/maddpg", "documents/api/learners/marl/mappo", "documents/api/learners/marl/masac", "documents/api/learners/marl/matd3", "documents/api/learners/marl/mfac", "documents/api/learners/marl/mfq", "documents/api/learners/marl/qmix", "documents/api/learners/marl/qtran", "documents/api/learners/marl/vdac", "documents/api/learners/marl/vdn", "documents/api/learners/marl/wqmix", "documents/api/policies", "documents/api/policies/categorical", "documents/api/policies/categorical_marl", "documents/api/policies/coordination_graph", "documents/api/policies/deterministic", "documents/api/policies/deterministic_marl", "documents/api/policies/gaussian", "documents/api/policies/gaussian_marl", "documents/api/policies/mixers", "documents/api/representations", "documents/api/representations/cnn", "documents/api/representations/mlp", "documents/api/representations/rnn", "documents/api/runners", "documents/api/runners/runner_basic", "documents/api/runners/runner_drl", "documents/api/runners/runner_football", "documents/api/runners/runner_magent", "documents/api/runners/runner_pettingzoo", "documents/api/runners/runner_sc2", "documents/api/utils", "documents/api/utils/distributions", "documents/api/utils/input_reformat", "documents/api/utils/layers", "documents/api/utils/operations", "documents/api/utils/value_norm", "documents/benchmark/atari", "documents/benchmark/magent", "documents/benchmark/mpe", "documents/benchmark/mujoco", "documents/benchmark/toy", "documents/usage/basic_usage", "documents/usage/installation", "documents/usage/professional_usage", "index"], "filenames": ["documents/algorithms/drl/a2c.rst", "documents/algorithms/drl/c51.rst", "documents/algorithms/drl/ddpg.rst", "documents/algorithms/drl/ddqn.rst", "documents/algorithms/drl/dqn.rst", "documents/algorithms/drl/drqn.rst", "documents/algorithms/drl/dueldqn.rst", "documents/algorithms/drl/mpdqn.rst", "documents/algorithms/drl/noisydqn.rst", "documents/algorithms/drl/pdqn.rst", "documents/algorithms/drl/perdqn.rst", "documents/algorithms/drl/ppg.rst", "documents/algorithms/drl/ppo.rst", "documents/algorithms/drl/qrdqn.rst", "documents/algorithms/drl/sac.rst", "documents/algorithms/drl/sac_dis.rst", "documents/algorithms/drl/spdqn.rst", "documents/algorithms/drl/td3.rst", "documents/algorithms/drl/vpg.rst", "documents/algorithms/index_drl.rst", "documents/algorithms/index_marl.rst", "documents/algorithms/marl/coma.rst", "documents/algorithms/marl/dcg.rst", "documents/algorithms/marl/iddpg.rst", "documents/algorithms/marl/ippo.rst", "documents/algorithms/marl/iql.rst", "documents/algorithms/marl/isac.rst", "documents/algorithms/marl/maddpg.rst", "documents/algorithms/marl/mappo.rst", "documents/algorithms/marl/masac.rst", "documents/algorithms/marl/matd3.rst", "documents/algorithms/marl/mfac.rst", "documents/algorithms/marl/mfq.rst", "documents/algorithms/marl/qmix.rst", "documents/algorithms/marl/qtran.rst", "documents/algorithms/marl/vdac.rst", "documents/algorithms/marl/vdn.rst", "documents/algorithms/marl/wqmix.rst", "documents/api/agents.rst", "documents/api/agents/drl/a2c.rst", "documents/api/agents/drl/basic_drl_class.rst", "documents/api/agents/drl/c51.rst", "documents/api/agents/drl/ddpg.rst", "documents/api/agents/drl/ddqn.rst", "documents/api/agents/drl/dqn.rst", "documents/api/agents/drl/dueldqn.rst", "documents/api/agents/drl/mpdqn.rst", "documents/api/agents/drl/noisydqn.rst", "documents/api/agents/drl/pdqn.rst", "documents/api/agents/drl/perdqn.rst", "documents/api/agents/drl/pg.rst", "documents/api/agents/drl/ppg.rst", "documents/api/agents/drl/ppo_clip.rst", "documents/api/agents/drl/ppo_kl.rst", "documents/api/agents/drl/qrdqn.rst", "documents/api/agents/drl/sac.rst", "documents/api/agents/drl/sac_dis.rst", "documents/api/agents/drl/spdqn.rst", "documents/api/agents/drl/td3.rst", "documents/api/agents/marl/basic_marl_class.rst", "documents/api/agents/marl/coma.rst", "documents/api/agents/marl/dcg.rst", "documents/api/agents/marl/iddpg.rst", "documents/api/agents/marl/ippo.rst", "documents/api/agents/marl/iql.rst", "documents/api/agents/marl/isac.rst", "documents/api/agents/marl/maddpg.rst", "documents/api/agents/marl/mappo.rst", "documents/api/agents/marl/masac.rst", "documents/api/agents/marl/matd3.rst", "documents/api/agents/marl/mfac.rst", "documents/api/agents/marl/mfq.rst", "documents/api/agents/marl/qmix.rst", "documents/api/agents/marl/qtran.rst", "documents/api/agents/marl/vdac.rst", "documents/api/agents/marl/vdn.rst", "documents/api/agents/marl/wqmix.rst", "documents/api/common.rst", "documents/api/common/common_tools.rst", "documents/api/common/memory_tools.rst", "documents/api/common/memory_tools_marl.rst", "documents/api/common/segtree_tool.rst", "documents/api/common/statistic_tools.rst", "documents/api/configs.rst", "documents/api/environments.rst", "documents/api/learners.rst", "documents/api/learners/drl/a2c.rst", "documents/api/learners/drl/c51.rst", "documents/api/learners/drl/ddpg.rst", "documents/api/learners/drl/ddqn.rst", "documents/api/learners/drl/dqn.rst", "documents/api/learners/drl/dueldqn.rst", "documents/api/learners/drl/mpdqn.rst", "documents/api/learners/drl/noisydqn.rst", "documents/api/learners/drl/pdqn.rst", "documents/api/learners/drl/perdqn.rst", "documents/api/learners/drl/pg.rst", "documents/api/learners/drl/ppg.rst", "documents/api/learners/drl/ppo_clip.rst", "documents/api/learners/drl/ppo_kl.rst", "documents/api/learners/drl/qrdqn.rst", "documents/api/learners/drl/sac.rst", "documents/api/learners/drl/sac_dis.rst", "documents/api/learners/drl/spdqn.rst", "documents/api/learners/drl/td3.rst", "documents/api/learners/learner.rst", "documents/api/learners/marl/coma.rst", "documents/api/learners/marl/dcg.rst", "documents/api/learners/marl/iddpg.rst", "documents/api/learners/marl/ippo.rst", "documents/api/learners/marl/iql.rst", "documents/api/learners/marl/isac.rst", "documents/api/learners/marl/maddpg.rst", "documents/api/learners/marl/mappo.rst", "documents/api/learners/marl/masac.rst", "documents/api/learners/marl/matd3.rst", "documents/api/learners/marl/mfac.rst", "documents/api/learners/marl/mfq.rst", "documents/api/learners/marl/qmix.rst", "documents/api/learners/marl/qtran.rst", "documents/api/learners/marl/vdac.rst", "documents/api/learners/marl/vdn.rst", "documents/api/learners/marl/wqmix.rst", "documents/api/policies.rst", "documents/api/policies/categorical.rst", "documents/api/policies/categorical_marl.rst", "documents/api/policies/coordination_graph.rst", "documents/api/policies/deterministic.rst", "documents/api/policies/deterministic_marl.rst", "documents/api/policies/gaussian.rst", "documents/api/policies/gaussian_marl.rst", "documents/api/policies/mixers.rst", "documents/api/representations.rst", "documents/api/representations/cnn.rst", "documents/api/representations/mlp.rst", "documents/api/representations/rnn.rst", "documents/api/runners.rst", "documents/api/runners/runner_basic.rst", "documents/api/runners/runner_drl.rst", "documents/api/runners/runner_football.rst", "documents/api/runners/runner_magent.rst", "documents/api/runners/runner_pettingzoo.rst", "documents/api/runners/runner_sc2.rst", "documents/api/utils.rst", "documents/api/utils/distributions.rst", "documents/api/utils/input_reformat.rst", "documents/api/utils/layers.rst", "documents/api/utils/operations.rst", "documents/api/utils/value_norm.rst", "documents/benchmark/atari.rst", "documents/benchmark/magent.rst", "documents/benchmark/mpe.rst", "documents/benchmark/mujoco.rst", "documents/benchmark/toy.rst", "documents/usage/basic_usage.rst", "documents/usage/installation.rst", "documents/usage/professional_usage.rst", "index.rst"], "titles": ["A2C: Advantage Actor-Critic", "C51", "DDPG: Deep Deterministic Policy Gradient", "DDQN: Double Deep Q-Networks", "DQN", "DRQN", "Duel DQN", "MPDQN", "Noisy DQN", "PDQN", "Per DQN", "PPG", "PPO: Proximal Policy Optimization", "QRDQN", "Soft Actor-Critic", "Soft Actor-Critic for discrete action space", "SPDQN", "TD3", "Vanilla Policy Gradient", "Deep Reinforcement Learning", "Multi-Agent Reinforcement Learning", "COMA", "DCG", "IDDPG", "IPPO", "IQL: Independent Q-Learning", "ISAC", "MADDPG", "MAPPO", "MASAC", "MATD3", "MFAC", "MFQ", "QMIX", "QTRAN", "VDAC", "VDN: Value Decomposition Networks", "Weighted QMIX", "Agents", "A2C_Agent", "Agent", "C51_Agent", "DDPG_Agent", "DDQN_Agent", "DQN_Agent", "DuelDQN_Agent", "MPDQN_Agent", "NoisyDQN_Agent", "PDQN_Agent", "PerDQN_Agent", "PG_Agent", "PPG_Agent", "PPOCLIP_Agent", "PPOKL_Agent", "QRDQN_Agent", "SAC_Agent", "SACDIS_Agent", "SPDQN_Agent", "TD3_Agent", "MARLAgent", "COMA_Agents", "DCG_Agents", "IDDPG_Agents", "IPPO_Agents", "IQL_Agents", "ISAC_Agents", "MADDPG_Agents", "MAPPO_Agents", "MASAC_Agents", "MATD3_Agents", "MFAC", "MFQ_Agents", "QMIX_Agents", "QTRAN_Agents", "VDAC", "VDN_Agents", "WQMIX_Agents", "Common", "Common Tools", "Memory", "Memory for MARL", "Segment Tree", "Statistic Tools", "Configs", "Environments", "Learners", "A2C_Learner", "C51_Learner", "DDPG_Learner", "DDQN_Learner", "DQN_Learner", "DuelDQN_Learner", "MPDQN_Learner", "NoisyDQN_Learner", "PDQN_Learner", "PerDQN_Learner", "PG_Learner", "PPG_Learner", "PPOCLIP_Learner", "PPOKL_Learner", "QRDQN_Learner", "SAC_Learner", "SACDIS_Learner", "SPDQN_Learner", "TD3_Learner", "Learner", "COMA_Learner", "DCG_Learner", "IDDPG_Learner", "IPPO_Learner", "IQL_Learner", "ISAC_Learner", "MADDPG_Learner", "MAPPO_Learner", "MASAC_Learner", "MATD3_Learner", "MFAC_Learner", "MFQ_Learner", "QMIX_Learner", "QTRAN_Learner", "VDAC_Learner", "VDN_Learner", "WQMIX_Learner", "Policies", "Categorical", "Categorical-MARL", "Coordination-Graph", "Deterministic", "Deterministic-MARL", "Gaussian", "Gaussian-MARL", "Mixiers", "Representations", "CNN-based", "MLP-based", "RNN-based", "Runners", "Runner_Base", "Runner_DRL", "Runner_Football", "Runner_MAgent", "Runner_Pettingzoo", "Runner_SC2", "Utils", "Distributions", "Input Reformation", "Neural Network Layers", "Operations", "ValueNorm", "Atari benchmarks", "Magent benchmarks", "MPE benchmarks", "MuJoCo benchmarks", "Toy benchmarks", "Quick Start", "Installation", "Professional Usage", "Welcome to XuanCe\u2019s documentation!"], "terms": {"deep": [4, 5, 38, 85, 134, 136, 155, 156, 157], "q": [4, 5, 19, 20, 38, 43, 46, 48, 57, 85], "network": [4, 5, 19, 20, 38, 39, 50, 51, 52, 53, 85, 132, 133, 134, 135], "i": [4, 5, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 84, 105, 133, 134, 135, 154, 155, 156, 157], "valu": [4, 5, 20, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 67, 83, 85, 105, 123, 143], "base": [4, 5, 84, 123, 143, 156], "drl": [4, 5, 156, 157], "paper": [4, 5], "link": [4, 5, 154, 156], "human": [4, 46, 48, 57, 83, 156], "level": [4, 156], "control": [4, 84], "through": 4, "reinforc": [4, 38, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 85, 123, 136, 156, 157], "learn": [4, 5, 38, 39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 85, 105, 123, 136, 155, 156, 157], "bibtex": [4, 5], "citat": [4, 5], "articl": 4, "mnih2015human": 4, "titl": [4, 5], "author": [4, 5], "mnih": 4, "volodymyr": 4, "kavukcuoglu": 4, "korai": 4, "silver": 4, "david": 4, "rusu": 4, "andrei": 4, "A": [4, 133, 156], "veness": 4, "joel": 4, "bellemar": 4, "marc": 4, "g": 4, "grave": 4, "alex": 4, "riedmil": 4, "martin": 4, "fidjeland": 4, "andrea": 4, "k": [4, 40, 62, 65, 66, 68, 69, 133], "ostrovski": 4, "georg": 4, "other": 4, "journal": 4, "natur": 4, "volum": 4, "518": 4, "number": [4, 39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 83, 133, 156], "7540": 4, "page": [4, 156, 157], "529": 4, "533": 4, "year": [4, 5], "2015": [4, 5], "publish": [4, 152], "group": [4, 40], "dqn": [5, 19, 38, 43, 44, 45, 47, 83, 85, 154], "recurr": [5, 132, 135], "partial": 5, "observ": [5, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 133, 134, 156], "mdp": 5, "inproceed": 5, "hausknecht2015deep": 5, "hausknecht": 5, "matthew": 5, "stone": 5, "peter": 5, "booktitl": 5, "aaai": 5, "fall": 5, "symposium": 5, "seri": 5, "c51": 19, "ddqn": 19, "doubl": [19, 38, 43, 85], "duel": [19, 38, 45, 85], "noisi": [19, 38, 47, 85], "per": [19, 40, 156], "qrdqn": [19, 38, 54, 85], "drqn": 19, "vanilla": [19, 38, 85], "polici": [19, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 85, 105, 143, 154, 156, 157], "gradient": [19, 38, 85], "ppg": [19, 38, 51, 59, 85], "ppo": [19, 38, 52, 53, 85, 152, 156], "proxim": [19, 38, 85], "optim": [19, 38, 39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 85, 105, 156], "pdqn": [19, 38, 48, 85], "spdqn": [19, 38, 57, 85], "mpdqn": [19, 38, 46, 85], "a2c": [19, 38, 39, 59, 85, 152], "advantag": [19, 38, 85], "actor": [19, 38, 42, 55, 56, 58, 60, 67, 85, 133, 143], "critic": [19, 38, 39, 42, 50, 51, 52, 53, 55, 56, 58, 60, 67, 85, 133, 143], "soft": [19, 38, 85], "td3": [19, 38, 58, 85, 152], "ddpg": [19, 38, 42, 85, 152], "determinist": [19, 38, 85, 123], "iql": [20, 38, 85], "independ": [20, 38, 85], "vdn": [20, 38, 85], "decomposit": [20, 38, 85, 123], "qtran": [20, 38, 85], "qmix": [20, 38, 85], "weight": [20, 38, 49, 85, 133], "dcg": [20, 38, 85], "mfq": [20, 38, 85], "mfac": [20, 38, 59, 85], "mappo": [20, 38, 85], "coma": [20, 38, 59, 60, 85], "isac": [20, 38, 85], "masac": [20, 38, 85], "iddpg": [20, 38, 85, 154], "maddpg": [20, 38, 85, 154], "matd3": [20, 38, 85], "vdac": [20, 38, 59, 85], "pytorch": [38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 133, 134, 135, 155, 157], "tensorflow": [38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 133, 134, 135, 155, 157], "mindspor": [38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 133, 134, 135, 155, 156, 157], "checkmark": [38, 85], "c51dqn": [38, 41, 85], "distribut": [38, 51, 53, 85, 143], "paramet": [38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 85, 105, 133, 134, 135, 154, 156, 157], "space": [19, 38, 40, 46, 48, 57, 85, 123, 156], "nois": [38, 42, 58, 59, 62, 65, 66, 68, 69, 85], "perdqn": [38, 49, 85], "priorit": [38, 85], "experi": [38, 85], "replai": [38, 40, 59, 85], "quantil": [38, 85], "regress": [38, 85], "vpg": [38, 85], "phasic": [38, 85], "parameteris": [38, 85], "split": [38, 85], "multi": [38, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 85, 123, 132, 133, 134, 157], "pass": [38, 39, 41, 43, 44, 45, 46, 47, 48, 49, 50, 52, 53, 54, 56, 57, 85, 105], "sac": [38, 55, 85], "di": [38, 85], "discret": [19, 38, 46, 48, 57, 85, 123], "action": [19, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 83, 84, 85, 105, 123, 156], "twin": [38, 85], "delai": [38, 85], "mixer": [38, 72, 73, 75, 76, 85, 123], "wqmix": [38, 85], "transform": [38, 85], "coordin": [38, 85, 123], "graph": [38, 85, 123], "ippo": [20, 38, 85], "counterfacut": [38, 85], "pg": [38, 50, 59, 85], "mean": [38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 71, 85, 156, 157], "field": [38, 85], "class": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135], "xuanpolici": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 133, 134, 135, 152, 154, 155, 156], "torch": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 133, 134, 135, 154, 155, 156], "agent": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 84, 85, 123, 136, 154, 156, 157], "policy_gradi": [39, 42, 46, 48, 50, 51, 52, 53, 55, 56, 57, 58], "config": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 154, 157], "env": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 84, 154, 156], "schedul": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 105, 156], "devic": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 133, 134, 135, 156], "namespac": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105], "provid": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 135, 156], "hyper": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156, 157], "environ": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 136, 154, 155, 156, 157], "vector_env": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84], "vecenv": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84], "The": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135, 154, 155, 156], "vector": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 133, 134, 135, 136, 156], "nn": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 105, 133, 134, 135, 156], "modul": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 105, 133, 134, 135, 156, 157], "updat": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105], "lr_schedul": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 105, 156], "_lrschedul": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 105], "implement": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 84, 133, 134, 135, 156, 157], "rate": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 105, 156], "decai": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 105, 156], "str": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135, 156], "int": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 133, 134, 135, 156], "choos": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135, 154, 155], "cpu": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 133, 134, 135], "gpu": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 133, 134, 135], "train": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 133, 134, 135, 154, 156, 157], "model": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 133, 134, 135, 154], "_action": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "ob": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59], "calcul": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 133, 134, 135, 156], "accord": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 134, 154], "numpi": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 133, 134, 156], "ndarrai": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 133, 134], "current": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 71, 133, 134, 135, 156, 157], "step": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 64, 67, 71, 72, 73, 75, 76, 83, 84, 133, 134, 135, 155], "return": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135, 156], "v": [39, 40, 50, 51, 52, 53], "execut": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 59, 154], "type": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 133, 134, 135, 155, 156], "np": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 133, 134, 156], "train_step": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 156], "test": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 156], "env_fn": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 156], "test_episod": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 83, 156], "function": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 105, 133, 134, 135, 156], "make": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 156], "episod": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 62, 65, 66, 68, 69, 156], "score": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 156], "accumul": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "list": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 84, 143], "import": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 84, 105, 133, 134, 135, 154, 155, 156], "from": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135, 156, 157], "def": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135, 156], "__init__": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135], "self": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 105, 133, 134, 135], "dummyvecenv_gym": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "option": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 133, 134, 135], "none": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 133, 134, 135, 156], "union": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 133, 134, 135], "render": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 83, 84, 156], "n_env": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 60, 67, 156], "num_env": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156], "n_step": [39, 40, 50, 51, 52, 53, 156], "n_epoch": [39, 50, 51, 52, 53, 60, 67, 156], "n_minibatch": [39, 50, 51, 52, 53, 60, 67, 156], "gamma": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 156], "gae_lam": [39, 50, 51, 52, 53], "gae_lambda": [39, 50, 51, 52, 53, 60, 67, 156], "clip_grad": [39, 50], "observation_spac": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156], "action_spac": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 156], "auxiliary_info_shap": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "atari": [39, 41, 43, 44, 45, 47, 49, 50, 52, 53, 54, 56, 83, 84, 133, 157], "true": [39, 40, 41, 43, 44, 45, 46, 47, 48, 49, 50, 52, 53, 54, 56, 57, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 83, 135, 154, 156], "env_nam": [39, 41, 43, 44, 45, 47, 49, 50, 52, 53, 54, 56, 61, 83, 154, 156], "els": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105, 135, 156], "fals": [39, 40, 41, 43, 44, 45, 46, 47, 48, 49, 50, 52, 53, 54, 56, 57, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 135, 154, 156], "buffer": [39, 40, 41, 43, 44, 45, 47, 50, 52, 53, 54, 56, 59, 60, 61, 64, 67, 72, 75, 76], "dummyonpolicybuffer_atari": [39, 50, 52, 53], "dummyonpolicybuff": [39, 50, 51, 52], "buffer_s": [39, 50, 51, 52, 53, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "batch_siz": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83], "memori": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 77], "use_ga": [39, 50, 51, 52, 53, 60, 67, 156], "use_advnorm": [39, 50, 51, 52, 53, 60, 67, 156], "learner": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 157], "a2c_learn": 39, "model_dir": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 156], "vf_coef": [39, 52, 53, 156], "ent_coef": [39, 50, 51, 52, 53, 156], "super": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84, 133, 134, 135], "log_dir": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 156], "_": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 62, 64, 65, 66, 67, 68, 69, 72, 75, 76], "dist": [39, 50, 51, 52, 53, 65, 67, 68], "act": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 105], "stochastic_sampl": [39, 50, 51, 52, 53, 67], "detach": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 135], "buf_ob": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "tqdm": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "rang": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 67, 156], "step_info": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "obs_rm": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 105], "_process_observ": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "val": [39, 51, 52, 53], "next_ob": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "reward": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "termin": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 155], "trunction": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "info": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "store": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 84, 154], "_process_reward": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "full": [39, 50, 51, 52, 53, 60, 67, 157], "finish_path": [39, 50, 51, 52, 53], "0": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 84, 105, 133, 134, 135, 156], "index": [39, 50, 51, 52, 53, 60, 67, 135, 156, 157], "arang": [39, 50, 51, 52, 53, 60, 67], "random": [39, 41, 42, 43, 44, 45, 46, 48, 49, 50, 51, 52, 53, 54, 57, 58, 59, 60, 61, 62, 64, 66, 67, 69, 71, 72, 75, 76, 136, 156], "shuffl": [39, 50, 51, 52, 53, 60, 67], "start": [39, 50, 51, 52, 53, 59, 60, 67, 155, 156, 157], "end": [39, 50, 51, 52, 53, 59, 60, 67, 156], "sample_idx": [39, 50, 51, 52, 53, 60, 67], "obs_batch": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "act_batch": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "ret_batch": [39, 50, 51, 52, 53], "adv_batch": [39, 51, 52, 53], "sampl": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84], "log_info": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "current_step": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 156], "clear": [39, 50, 51, 52, 53, 60, 67], "ret_rm": [39, 40, 42, 46, 48, 50, 52, 53, 55, 56, 57, 58], "1": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 84, 105, 133, 134, 135, 152, 154, 155], "reset_ob": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "current_episod": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "use_wandb": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "d": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 156], "episode_step": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "episode_scor": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "test_env": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "video": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "episode_video": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "best_scor": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "inf": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "reset": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 84, 156], "render_mod": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 83, 156], "rgb_arrai": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 83, 156], "imag": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 133], "idx": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "img": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "enumer": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "append": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 62, 65, 66, 68, 69, 133], "while": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "ret": [39, 51, 52, 53], "copi": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 156], "test_mod": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 83, 156], "print": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 105, 156], "2f": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 156], "time": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 84, 105], "height": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 133], "width": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 133], "channel": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 133], "videos_info": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "videos_test": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "arrai": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 62, 65, 66, 68, 69, 71], "dtype": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 133, 134], "uint8": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "transpos": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 133], "4": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 83, 105, 152, 155], "2": [39, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 61, 67, 69, 71, 83, 84, 105, 133, 152, 154, 155], "3": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 83, 105, 133, 152, 155], "log_video": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "fp": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "50": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "x_index": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "best": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 156], "test_info": [39, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58], "std": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 156], "close": [39, 40, 41, 42, 43, 44, 45, 47, 49, 50, 51, 52, 53, 54, 55, 56, 58, 84, 156], "To": [40, 59, 84, 105, 133, 134, 135], "creat": [40, 59, 60, 67, 84, 105, 133, 134, 135, 136, 143, 154, 155], "new": [40, 59, 105, 135, 155], "you": [40, 59, 84, 105, 133, 134, 135, 154, 155, 156], "should": [40, 59, 105, 155, 156], "build": [40, 59, 60, 67, 105, 154, 156], "inherit": [40, 59, 84, 105], "common": [40, 59, 156, 157], "memory_tool": [40, 59], "experic": [40, 59], "directori": [40, 59, 84, 105, 154, 155, 156], "log": [40, 52, 59, 83, 154, 156], "file": [40, 59, 84, 105, 134, 154], "default": [40, 59, 83, 105, 156], "save_model": [40, 46, 48, 57, 59, 105, 156], "model_nam": [40, 59, 105, 156], "save": [40, 46, 48, 57, 59, 84, 105, 154, 156], "": [40, 59, 105, 133, 154], "name": [40, 59, 84, 134, 154, 156], "load_model": [40, 46, 48, 57, 59, 105, 156], "path": [40, 59, 105, 154, 156], "seed": [40, 59, 83, 84, 105, 136, 156], "load": [40, 59, 105, 156], "specifi": [40, 59, 105, 133, 134, 135, 154], "where": [40, 59, 105], "select": [40, 59, 60, 61, 64, 67, 71, 72, 75, 76, 105, 135], "wa": [40, 59, 105], "exit": [40, 59, 105], "visual": [40, 154], "inform": [40, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 135, 154, 156], "via": 40, "wandb": [40, 83, 154, 156], "tensorboard": [40, 83, 154, 156], "dict": [40, 46, 48, 57, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 133, 134, 135], "interact": 40, "between": 40, "upload": 40, "frame": [40, 83], "second": 40, "normal": [40, 42, 58, 62, 66, 69, 133, 134, 135, 143, 156], "origin": [40, 134], "get": [40, 59, 60, 67, 135, 143], "finish": [40, 156], "tensorflowtensorflow": 40, "mindsporetensorflow": 40, "abc": [40, 105], "comm": [40, 46, 48, 57], "mpi": [40, 46, 48, 57], "comm_world": [40, 46, 48, 57], "runningmeanstd": [40, 46, 48, 57], "shape": [40, 42, 46, 48, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 133, 134, 135], "space2shap": [40, 46, 48, 57, 156], "use_mpi": [40, 46, 48, 57], "use_obsnorm": [40, 46, 48, 57, 83, 156], "use_rewnorm": [40, 46, 48, 57, 83, 156], "obsnorm_rang": [40, 46, 48, 57, 83, 156], "rewnorm_rang": [40, 46, 48, 57, 83, 156], "zero": [40, 46, 48, 57, 135], "float32": [40, 46, 48, 57, 59, 133, 134], "time_str": 40, "asctim": 40, "replac": 40, "f": [40, 105, 133, 156], "seed_": [40, 105], "model_dir_sav": [40, 59], "o": [40, 59, 105, 156], "join": [40, 59, 105, 156], "getcwd": [40, 156], "exist": [40, 105, 156], "makedir": 40, "logger": [40, 83, 156], "writer": [40, 59], "summarywrit": [40, 59], "elif": [40, 73], "config_dict": 40, "var": 40, "wandb_dir": 40, "init": [40, 133, 156], "project": [40, 157], "project_nam": [40, 83, 156], "entiti": 40, "wandb_user_nam": [40, 83, 154, 156], "note": [40, 155], "socket": 40, "gethostnam": 40, "dir": 40, "env_id": [40, 83, 84, 154, 156], "job_typ": 40, "reinit": 40, "wandb_sil": 40, "rais": [40, 59, 73, 105], "No": 40, "model_dir_load": [40, 59, 156], "create_directori": [40, 59], "int32": [40, 46, 48, 57, 59], "model_path": [40, 59, 105], "item": 40, "try": 40, "add_scalar": 40, "except": 40, "format": [40, 73], "gif": 40, "add_video": 40, "global_step": 40, "isinst": [40, 46, 48, 57], "kei": [40, 46, 48, 57], "clip": [40, 42, 46, 48, 57, 58, 62, 65, 66, 68, 69], "ep": [40, 46, 48, 57, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156], "100": [40, 46, 48, 57], "abstractmethod": [40, 105], "notimplementederror": [40, 59, 105], "tk": [40, 59], "logdir": [40, 59, 154], "modeldir": [40, 59], "cell": [40, 59, 135], "qlearning_famili": [41, 43, 44, 45, 47, 49, 54], "egreedi": [41, 43, 44, 45, 46, 47, 48, 49, 54, 57, 60, 61, 64, 71, 72, 73, 75, 76], "float": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 57, 58, 59, 71, 133], "epsilong": [41, 43, 44, 45, 46, 47, 48, 49, 54, 57], "greedi": [41, 43, 44, 45, 46, 47, 48, 49, 54, 57, 60, 61, 64, 67, 71, 72, 75, 76], "factor": [41, 43, 44, 45, 46, 47, 48, 49, 54, 57, 59], "train_frequ": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 55, 56, 57, 58], "training_frequ": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 55, 56, 57, 58, 59, 83], "start_train": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 55, 56, 57, 58, 59, 61, 64, 71, 72, 75, 76, 83], "start_greedi": [41, 43, 44, 45, 49, 54, 60, 61, 64, 71, 72, 73, 75, 76, 83], "end_greedi": [41, 43, 44, 45, 49, 54, 60, 61, 64, 71, 72, 73, 75, 76, 83], "dummyoffpolicybuffer_atari": [41, 43, 44, 45, 47, 54, 56], "dummyoffpolicybuff": [41, 42, 43, 44, 45, 46, 47, 48, 54, 55, 56, 57, 58], "n_size": [41, 42, 43, 44, 45, 47, 49, 54, 55, 56, 58, 60, 67, 83], "c51_learner": 41, "sync_frequ": [41, 43, 44, 45, 47, 49, 54, 60, 61, 64, 71, 72, 73, 75, 76, 83], "argmax_act": [41, 43, 44, 45, 47, 49, 54], "random_act": [41, 43, 44, 45, 49, 54, 59, 61, 64, 71, 72, 75, 76], "choic": [41, 43, 44, 45, 46, 48, 49, 54, 57, 61, 64, 72, 75, 76, 83, 134, 156], "n": [41, 43, 44, 45, 46, 48, 49, 54, 57, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76, 155], "rand": [41, 43, 44, 45, 46, 48, 49, 54, 57, 61, 64, 71, 72, 75, 76], "rew_batch": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 55, 56, 57, 58], "terminal_batch": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 55, 56, 57, 58], "next_batch": [41, 42, 43, 44, 45, 46, 47, 48, 49, 54, 55, 56, 57, 58], "epsilon": [41, 43, 44, 45, 46, 48, 49, 54, 57, 59, 60, 61, 64, 67, 71, 72, 75, 76], "decay_step_greedi": [41, 43, 44, 45, 49, 54, 60, 61, 64, 71, 72, 73, 75, 76, 83], "noise_scal": [42, 46, 47, 48, 55, 56, 57, 58], "varianc": [42, 58], "gaussian": [42, 58, 123, 156], "sequenc": [42, 46, 48, 55, 56, 57, 58, 67, 105, 133, 134, 135], "start_nois": [42, 46, 47, 48, 55, 56, 57, 58], "end_nois": [42, 46, 47, 48, 55, 56, 57, 58], "delta_nois": 42, "running_step": [42, 58, 83, 105, 156], "ddpg_learner": 42, "tau": [42, 46, 48, 55, 56, 57, 58], "size": [42, 58, 62, 66, 69, 133, 135], "trick": [43, 83, 157], "ddqn_learner": 43, "dqn_learner": [44, 47], "dueldqn_learn": 45, "disact": [46, 48, 57], "conact": [46, 48, 57], "con_act": [46, 48, 57], "continu": [46, 48, 57, 123, 156], "pad_act": [46, 48, 57], "tupl": [46, 48, 57, 60, 61, 64, 67, 71, 72, 75, 76, 133, 135], "gym": [46, 48, 57, 83, 84, 156], "gym_env": [46, 48, 57], "old_a": [46, 48, 57], "num_disact": [46, 48, 57], "box": [46, 48, 57, 84, 157], "low": [46, 48, 57, 62, 65, 66, 68, 69], "high": [46, 48, 57, 62, 65, 66, 68, 69, 157], "action_high": [46, 48, 57], "action_low": [46, 48, 57], "action_rang": [46, 48, 57], "representation_info_shap": [46, 48, 50, 51, 53, 57, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76], "state": [46, 48, 57, 59, 60, 61, 64, 67, 71, 72, 75, 76, 133, 134, 135], "nenv": [46, 48, 57, 59, 61, 64, 72, 75, 76], "epsilon_step": [46, 48, 57], "1000": [46, 48, 57, 152], "epsilon_initi": [46, 48, 57], "epsilon_fin": [46, 48, 57], "buffer_action_spac": [46, 48, 57], "ones": [46, 48, 57, 156], "float64": [46, 48, 57], "nsize": [46, 48, 57], "batchsiz": [46, 48, 57], "pdqn_learner": [46, 48, 57], "conact_s": [46, 48, 57], "sum": [46, 48, 57, 71], "no_grad": [46, 48, 57, 61], "as_tensor": [46, 48, 57, 133, 134], "rnd": [46, 48, 57], "qeval": [46, 48, 57], "unsqueez": [46, 48, 57, 60, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "data": [46, 48, 57, 133, 135], "argmax": [46, 48, 57], "offset": [46, 48, 57], "10000": [46, 48, 57, 83, 156], "episode_info": [46, 48, 57], "concaten": [46, 48, 57], "axi": [46, 48, 57, 67], "ravel": [46, 48, 57], "end_episod": [46, 48, 57], "50000": [46, 48, 57], "npy": [46, 48, 57, 105], "count": [46, 48, 57], "test_step": [46, 48, 57, 83, 156], "evalu": [46, 48, 57], "decay_step_nois": 47, "update_nois": 47, "per_beta0": 49, "per_beta": 49, "peroffpolicybuff": 49, "per_alpha": 49, "perdqn_learn": 49, "td_error": 49, "update_prior": 49, "represent": [50, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 133, 134, 135, 143, 156, 157], "output_shap": [50, 51, 53, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 133, 134, 135], "pg_learner": 50, "stochast": [51, 53, 143], "policy_nepoch": 51, "value_nepoch": 51, "aux_nepoch": 51, "actor_represent": 51, "old_dist": [51, 53], "ppg_learner": 51, "clip_rang": [51, 52, 156], "kl_beta": 51, "split_distribut": [51, 53], "aux_batch": [51, 52, 53], "update_polici": 51, "update_crit": 51, "old_prob": 51, "buffer_ob": 51, "buffer_act": 51, "new_dist": 51, "auxiliary_info": 51, "update_auxiliari": 51, "logp": [51, 52, 53], "probabl": 52, "old_logp": [52, 53], "ppoclip_learn": 52, "clip_grad_norm": [52, 156], "use_grad_clip": [52, 156], "log_prob": [52, 67], "value_batch": [52, 53], "representation_actor": 53, "ppokl_learn": 53, "target_kl": [53, 156], "qrdqn_learner": 54, "sac_learn": 55, "act_dist": 55, "sacdi": 56, "sacdis_learn": 56, "act_prob": 56, "act_distribut": 56, "td3_learner": 58, "actor_update_delai": 58, "marl": [59, 77, 123], "agents_marl": [59, 60, 71, 73], "learnerma": [59, 105], "kwarg": [59, 105, 135], "joint": [59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "global": [59, 60, 67], "avail": [59, 60, 61, 64, 67, 72, 75, 76], "etc": [59, 84, 154, 155], "input": [59, 60, 67, 133, 134, 135, 143, 156], "info_train": [59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "linear_decay_or_increas": [59, 60, 71, 73], "step_length": 59, "increas": 59, "onc": 59, "randomag": 59, "arg": [59, 62, 66, 69, 71, 73, 105, 156], "output": [59, 62, 65, 66, 68, 69, 133, 134, 135], "object": 59, "dummyvecenv_pettingzoo": [59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "basebuff": 59, "n_agent": [59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 105], "dim_ob": [59, 67, 105], "dim_act": [59, 60, 61, 64, 67, 71, 72, 73, 75, 76, 105], "dim_id": [59, 105], "cuda": [59, 83, 105, 156], "is_avail": [59, 105], "is_decai": 59, "delta": 59, "max": 59, "min": 59, "agent_kei": [59, 61, 62, 65, 66, 68, 69, 71, 73], "obs_n": [59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "rand_a": 59, "e": [59, 155], "handl": 59, "agent_index": 59, "agent_id": 59, "epsilon_decai": [59, 73], "agents_id": [59, 60, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "tile": 59, "expand_dim": 59, "ey": [59, 60, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "reshap": [59, 60, 64, 67, 72, 75, 76], "obs_in": [59, 60, 61, 64, 67, 71, 72, 75, 76], "id": [59, 105, 156], "greedy_act": [59, 61, 64, 71, 72, 75, 76], "random_vari": 59, "action_pick": 59, "i_episod": [59, 62, 65, 66, 68, 69, 73], "get_total_it": [59, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 156], "agent_nam": [59, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 154, 156], "ppo_clip": [59, 156], "ppo_kl": [59, 156], "mappo_clip": 59, "mappo_kl": 59, "training_step": 59, "nepoch": 59, "nminibatch": 59, "nstep": 59, "m": 59, "op": [59, 83], "tensor": [59, 60, 61, 62, 64, 66, 67, 69, 71, 72, 75, 76, 133, 134, 135], "dummyvecenv_ma": [59, 84], "expanddim": 59, "broadcast_to": 59, "view": [59, 60, 61, 64, 67, 72, 75, 76, 154], "asnumpi": 59, "a3c": 59, "mutli_agent_rl": [60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "rnn_hidden": [60, 61, 64, 67, 71, 72, 75, 76, 135], "avail_act": [60, 61, 64, 67, 72, 75, 76], "hidden": [60, 61, 64, 67, 71, 72, 75, 76, 133, 135], "rnn": [60, 61, 64, 67, 71, 72, 75, 76, 132, 143], "mask": [60, 61, 64, 67, 71, 72, 75, 76], "bool": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "hidden_st": [60, 61, 64, 67, 71, 72, 75, 76, 135], "actions_n": [60, 61, 64, 67, 71, 72, 75, 76], "onehot_act": [60, 71, 105], "next": [60, 61, 64, 67, 71, 72, 75, 76, 155], "onehot": 60, "i_step": [60, 61, 64, 67, 71, 72, 73, 75, 76], "th": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "dure": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156], "process": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 133, 134, 135, 154, 156, 157], "marlag": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "delta_egreedi": [60, 61, 64, 71, 72, 73, 75, 76], "state_spac": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "dim_stat": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 84], "state_shap": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "input_represent": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "get_repre_in": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "use_recurr": [60, 61, 64, 67, 71, 72, 75, 76], "use_global_st": [60, 67], "kwargs_rnn": [60, 61, 64, 67, 72, 75, 76], "n_recurrent_lay": [60, 61, 64, 67, 72, 75, 76, 135], "dropout": [60, 61, 64, 67, 72, 75, 76, 135], "registry_represent": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "input_polici": [60, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "get_policy_in_marl": [60, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "registry_polici": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "gain": [60, 67, 133], "adam": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156], "parameters_actor": [60, 62, 65, 66, 68, 69], "learning_rate_actor": 60, "1e": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 156], "5": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 83, 105, 152, 155, 156], "parameters_crit": [60, 62, 65, 66, 68], "learning_rate_crit": 60, "linearlr": [60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 156], "start_factor": [60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 156], "end_factor": [60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 156], "total_it": [60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 75, 76, 156], "act_onehot_shap": 60, "act_shap": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "coma_buffer_rnn": 60, "coma_buff": 60, "input_buff": [60, 61, 64, 67, 72, 75, 76], "obs_shap": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "rew_shap": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "done_shap": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "max_episode_length": [60, 61, 64, 67, 72, 75, 76], "td_lambda": 60, "coma_learn": 60, "on_polici": [60, 61, 62, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76], "len": [60, 62, 65, 66, 67, 68, 69, 134], "expand": [60, 62, 64, 65, 66, 67, 68, 69, 71, 72, 75, 76], "batch_ag": [60, 64, 67, 72, 75, 76], "action_prob": 60, "picked_act": 60, "categor": [60, 61, 64, 72, 75, 76, 123], "actions_onehot": 60, "actions_in": 60, "repeat": [60, 71], "agent_mask": [60, 71], "critic_in": [60, 67], "concat": 60, "dim": [60, 71], "values_n": [60, 67], "get_valu": [60, 67], "target": 60, "target_valu": 60, "gather": 60, "long": [60, 105], "update_recurr": [60, 61, 64, 67, 72, 75, 76, 105], "repre_state_dim": 61, "coordination_graph": 61, "dcg_util": 61, "dcg_payoff": 61, "util": [61, 133, 134, 135, 156, 157], "hidden_utility_dim": 61, "payoff": 61, "hidden_payoff_dim": 61, "dcgraph": 61, "graph_typ": 61, "set_coordination_graph": 61, "starcraft2": [61, 84, 136], "dcg_": 61, "hidden_bias_dim": 61, "relu": [61, 83], "learning_r": [61, 64, 67, 71, 72, 73, 75, 76, 83, 156], "marl_offpolicybuffer_rnn": [61, 64, 72, 75, 76], "marl_offpolicybuff": [61, 62, 64, 65, 66, 68, 69, 72, 73, 75, 76], "multi_agent_rl": 61, "dcg_learner": 61, "rnn_hidden_next": 61, "get_hidden_st": [61, 105], "add": [62, 65, 66, 67, 68, 69], "If": [62, 65, 66, 68, 69, 84, 154, 155, 156], "directli": [62, 65, 66, 68, 69, 134, 156], "lr_a": [62, 65, 66, 68, 69], "lr_c": [62, 65, 66, 68, 69], "actions_high": [62, 65, 66, 68, 69], "actions_low": [62, 65, 66, 68, 69], "iddpg_learn": 62, "sigma": [62, 66, 69], "iql_learn": 64, "isac_learn": 65, "rsampl": [65, 68], "maddpg_learn": 66, "representation_crit": 67, "lr": 67, "weight_decai": 67, "marl_onpolicybuffer_rnn": 67, "marl_onpolicybuff": 67, "mappo_clip_learn": 67, "share_valu": 67, "log_pi_a": 67, "length": 67, "squeez": 67, "lr_decai": [67, 105], "masac_learn": 68, "critic_net_a": 69, "critic_net_b": 69, "matd3_learn": 69, "mfac\u7b97\u6cd5\u7684\u5168\u79f0\u662fmean": [], "\u662f\u4e00\u79cd\u57fa\u4e8eactor": [], "critic\u7684\u591a\u667a\u80fd\u4f53\u5f3a\u5316\u5b66\u4e60\u7b97\u6cd5": [], "\u5176\u57fa\u672c\u601d\u60f3\u548cmfq\u7b97\u6cd5\u76f8\u540c": [], "\u5c06\u667a\u80fd\u4f53\u7684\u5c40\u90e8\u89c2\u6d4b": [], "\u5c40\u90e8\u52a8\u4f5c\u548c\u90bb\u5c45\u667a\u80fd\u4f53\u7684\u5e73\u5747\u52a8\u4f5c\u4f5c\u4e3a\u7f51\u8def\u7684\u8f93\u5165": [], "mfac\u91c7\u7528actor": [], "critic\u7ed3\u6784\u5b9e\u73b0\u7b56\u7565\u7684\u66f4\u65b0": [], "\u7f51\u8def\u7ed3\u6784\u548ca2c\u76f8\u4f3c": [], "\u8be5\u7b97\u6cd5\u7684\u7f16\u5199\u53c2\u8003\u5982\u4e0b\u6587\u732e": [], "\u8bba\u6587\u5f15\u7528\u4fe1\u606f": [], "yang2018mean": [], "yang": [], "yaodong": [], "luo": [], "rui": [], "li": [], "minn": [], "zhou": [], "ming": [], "zhang": [], "weinan": [], "wang": [], "jun": [], "intern": 156, "confer": [], "machin": [], "5571": [], "5580": [], "2018": [], "organ": [], "pmlr": [], "act_mean": 71, "variabl": [71, 133, 135, 143, 156], "act_mean_curr": 71, "meanfield_offpolicybuff": 71, "act_prob_shap": 71, "mfq_learner": 71, "q_output": 71, "n_aliv": 71, "action_n_mask": 71, "act_neighbor_sampl": 71, "sample_act": 71, "logit": 71, "act_neighbor_onehot": 71, "qmix_mix": [72, 76], "hidden_dim_mixing_net": [72, 76], "hidden_dim_hyper_net": [72, 76], "qmix_learn": 72, "vdn_mixer": [73, 75], "qtran_bas": 73, "qtran_net": 73, "qtran_net_hidden_dim": 73, "q_hidden_s": [73, 83], "qtran_alt": 73, "valueerror": 73, "recognis": 73, "qtran_mix": 73, "qtran_learn": 73, "greedy_update_step": 73, "can_sampl": 73, "vdac\u7b97\u6cd5\u5168\u79f0\u4e3avalu": [], "vdac\u7b97\u6cd5\u53d1\u626c\u4e86vdn\u7b97\u6cd5\u548ca2c\u7b97\u6cd5\u7684\u4f18\u52bf": [], "\u5c06\u503c\u51fd\u6570\u5206\u89e3\u601d\u60f3\u5f15\u5165actor": [], "critic\u7ed3\u6784\u4e2d": [], "\u5b9e\u73b0\u591a\u667a\u80fd\u4f53\u5206\u5e03\u5f0f\u7b56\u7565\u7684\u4f18\u5316": [], "\u5728\u672c\u7b97\u6cd5\u5e93\u4e2d": [], "vdac\u7684\u7ed3\u6784\u548ca2c\u76f8\u540c": [], "\u4e0d\u540c\u4e4b\u5904\u5728\u4e8evdac\u5c06\u5404\u667a\u80fd\u4f53\u72ec\u7acb\u7684q\u503c\u7ecf\u8fc7vdn": [], "mixer\u5f97\u5230\u6574\u4f53q\u503c": [], "\u8fdb\u800c\u5b9e\u73b0\u7aef\u5230\u7aef\u8bad\u7ec3": [], "\u8be5\u7b97\u6cd5\u7684\u7f16\u5199\u53c2\u8003\u5982\u4e0b\u8bba\u6587": [], "su2021valu": [], "su": [], "jianyu": [], "stephen": [], "bele": [], "proceed": [], "artifici": [], "intellig": [], "35": [], "13": [], "11352": [], "11360": [], "2021": [], "vdn_learner": 75, "alpha": 76, "ff_mixer": 76, "qmix_ff_mix": 76, "hidden_dim_ff_mix_net": 76, "wqmix_learn": 76, "tool": [77, 105, 123, 143, 154], "segment": 77, "tree": 77, "statist": 77, "\u57fa\u7840\u53c2\u6570\u914d\u7f6e\u5b58\u4e8exuanpolici": 83, "basic": [83, 105, 136, 143, 154], "yaml\u6587\u4ef6\u4e2d": 83, "\u793a\u4f8b\u5982\u4e0b": 83, "dl_toolbox": [83, 156], "tensorlay": [83, 156], "xuance_benchmark": [83, 156], "papers_liu": 83, "parallel": [83, 156], "10": 83, "2910": 83, "2000": 83, "\u9700\u8981\u6ce8\u610f\u7684\u662f": 83, "yaml": [83, 154, 156], "\u6587\u4ef6\u4e2d\u7684": 83, "\u53d8\u91cf\u53d6\u503c\u6839\u636e\u4e0d\u540c\u7684\u6df1\u5ea6\u5b66\u4e60\u6846\u67b6\u6709\u6240\u5dee\u5f02": 83, "\u5206\u522b\u5982\u4e0b": 83, "ascend": 83, "davinci": 83, "\u4ee5dqn\u7b97\u6cd5\u5728atari\u73af\u5883\u4e2d\u7684\u53c2\u6570\u914d\u7f6e\u4e3a\u4f8b": 83, "\u9664\u4e86\u57fa\u7840\u53c2\u6570\u914d\u7f6e\u5916": 83, "\u5176\u7b97\u6cd5\u53c2\u6570\u914d\u7f6e\u5b58\u653e\u4e8e": 83, "\u6587\u4ef6\u4e2d": 83, "\u5185\u5bb9\u5982\u4e0b": 83, "dummy_atari": 83, "al": 83, "breakout": 83, "v5": 83, "obs_typ": 83, "grayscal": 83, "ram": 83, "rgb": 83, "img_siz": 83, "84": 83, "210": 83, "x": [83, 133, 135], "160": 83, "num_stack": 83, "stack": [83, 133, 134], "frame_skip": 83, "skip": 83, "noop_max": 83, "30": 83, "do": 83, "basic_q_network": 83, "basic_cnn": [83, 133], "follow": [83, 84, 154, 155, 156], "three": [83, 156], "argument": [83, 156], "ar": [83, 84, 133, 135, 154, 155, 156, 157], "filter": [83, 133], "32": 83, "64": 83, "16": [83, 156], "kernel": [83, 133], "8": [83, 152, 156], "6": [83, 105, 152], "stride": [83, 133], "512": 83, "activ": [83, 133, 134, 135, 155, 156], "1069": 83, "100000": 83, "0001": 83, "99": [83, 152, 156], "05": [83, 152], "1000000": [83, 156], "1m": 83, "500": 83, "50000000": 83, "50m": 83, "eval_interv": [83, 156], "500000": 83, "\u7531\u4e8eatari\u73af\u5883\u4e2d\u4e00\u5171\u8d85\u8fc760\u4e2a\u4e0d\u540c\u573a\u666f": 83, "\u573a\u666f\u6bd4\u8f83\u7edf\u4e00": 83, "\u53ea\u662f\u4efb\u52a1\u4e0d\u540c": 83, "\u56e0\u6b64\u53ea\u9700\u8981\u4e00\u4e2a\u9ed8\u8ba4\u7684\u53c2\u6570\u914d\u7f6e\u6587\u4ef6\u5373\u53ef": 83, "\u9488\u5bf9\u573a\u666f\u5dee\u5f02\u8f83\u5927\u7684\u73af\u5883": 83, "\u5982": 83, "box2d": [83, 84], "\u73af\u5883\u4e2d\u7684": 83, "carrac": 83, "v2": 83, "\u548c": 83, "lunarland": 83, "\u573a\u666f": 83, "\u524d\u8005\u7684\u72b6\u6001\u8f93\u5165\u662f96": 83, "96": 83, "3\u7684rgb\u56fe\u50cf": 83, "\u540e\u8005\u5219\u662f\u4e00\u4e2a8\u7ef4\u5411\u91cf": 83, "\u56e0\u6b64": 83, "\u9488\u5bf9\u8fd9\u4e24\u4e2a\u573a\u666f\u7684dqn\u7b97\u6cd5\u53c2\u6570\u914d\u7f6e\u5206\u522b\u5b58\u4e8e\u4ee5\u4e0b\u4e24\u4e2a\u6587\u4ef6\u4e2d": 83, "\u7528\u6237\u4e5f\u53ef\u4ee5\u9009\u62e9\u4e0d\u9002\u7528\u7384\u7b56\u63d0\u4f9b\u7684\u9ed8\u8ba4\u53c2\u6570": 83, "\u6216\u8005\u7384\u7b56\u4e2d\u4e0d\u5305\u542b\u7528\u6237\u7684\u4efb\u52a1\u65f6": 83, "\u53ef\u7528\u540c\u6837\u7684\u65b9\u5f0f\u81ea\u5b9a\u4e49": 83, "yaml\u53c2\u6570\u914d\u7f6e\u6587\u4ef6": 83, "\u4f46\u662f\u5728\u83b7\u53d6runner\u7684\u8fc7\u7a0b\u4e2d": 83, "\u9700\u6307\u5b9a\u53c2\u6570\u6587\u4ef6\u7684\u5b58\u653e\u4f4d\u7f6e": 83, "xp": [83, 154], "runner": [83, 154, 156, 157], "get_runn": [83, 154], "method": [83, 133, 134, 135, 154, 156], "classic_control": [83, 154], "cartpol": [83, 154], "v1": [83, 154], "config_path": [83, 156], "xxx": 83, "is_test": [83, 154], "run": [83, 84, 133, 134, 135, 155], "softwar": [84, 135], "singl": [84, 133, 136], "task": [84, 133, 152, 154, 156], "simul": [84, 156], "mujoco": [84, 156, 157], "classic": 84, "under": 84, "It": [84, 155], "also": [84, 133, 134, 135, 154, 155], "mpe": [84, 154, 157], "sisl": 84, "open": [84, 155, 157], "sourc": [84, 155, 156, 157], "pettingzoo": [84, 136], "magent2": [84, 136], "googl": [84, 136], "footbal": [84, 136], "each": [84, 133, 135], "contain": [84, 135, 143, 154, 156], "rich": 84, "varieti": 84, "scenario": [84, 135], "shown": 84, "tabl": 84, "below": 84, "us": [84, 105, 133, 134, 135, 154, 155, 156], "user": [84, 134, 154, 156], "can": [84, 134, 135, 154, 155, 156, 157], "wrap": 84, "specif": [84, 154], "ad": 84, "\u6b65\u9aa4\u4e00": [], "my_env": 84, "make_env": [84, 156], "obeservation_spac": 84, "metadata": 84, "reward_rang": 84, "spec": 84, "mode": 84, "\u6b65\u9aa4\u4e8c": [], "\u5728": [], "py\u6587\u4ef6\u4e2d\u5bfc\u5165\u81ea\u5b9a\u4e49\u7684\u73af\u5883\u7c7bmy_env": [], "myenv": 84, "\u4e3a\u4e86\u63d0\u9ad8\u91c7\u6837\u6548\u7387": [], "\u8282\u7701\u7b97\u6cd5\u8fd0\u884c\u65f6\u95f4": [], "\u672c\u8f6f\u4ef6\u652f\u6301\u5411\u91cf\u5316\u4eff\u771f\u73af\u5883\u8bbe\u7f6e": [], "\u5373\u8fd0\u884c\u591a\u4e2a\u4eff\u771f\u73af\u5883\u540c\u65f6\u91c7\u6837": [], "\u5411\u91cf\u5316\u73af\u5883\u57fa\u7c7bvecenv\u7684\u5b9a\u4e49\u4f4d\u4e8e": [], "py\u6587\u4ef6\u4e2d": [], "\u5728\u6b64\u57fa\u7c7b\u4e0a\u5b9a\u4e49\u7ee7\u627f\u7c7bdummyvecenv\u53cadummyvecenv_ma": [], "\u5206\u522b\u7528\u4e8e\u5b9e\u73b0\u5355\u667a\u80fd\u4f53\u548c\u591a\u667a\u80fd\u4f53\u5411\u91cf\u5316\u4eff\u771f\u73af\u5883": [], "\u4ee3\u7801\u4f4d\u4e8e": [], "dummy_vec_env": 84, "paramt": 105, "argpars": [105, 156], "iter": 105, "state_dict": 105, "file_nam": 105, "listdir": 105, "chang": [105, 155], "break": 105, "remov": 105, "sort": 105, "load_state_dict": 105, "map_loc": 105, "7": [105, 152, 155], "value_norm": 105, "set_devic": 105, "gpu_id": 105, "actions_int": 105, "num_act": 105, "one_hot": 105, "num_class": 105, "system": 123, "either": 123, "discrtet": 123, "contin": 123, "mixier": 123, "algorithm": [84, 123, 133, 143, 154, 156], "mlp": [132, 133, 135, 143], "layer": [132, 133, 134, 135, 143], "perceptron": [132, 134], "cnn": [132, 143], "convolut": [132, 133], "neural": [132, 133, 134, 135], "\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u4e3b\u8981\u7528\u4e8e\u5904\u7406\u56fe\u50cf\u8f93\u5165\u6570\u636e": [], "\u63d0\u53d6\u51fa\u7279\u5f81\u5411\u91cf": [], "\u4e00\u822c\u8f93\u5165\u7c7b\u578b\u4e3a\u591a\u901a\u9053\u56fe\u50cf\u77e9\u9635": [], "\u8f93\u51fa\u591a\u7ef4\u5411\u91cf": [], "\u540d\u79f0\u4e3a": [], "cnn_block": 133, "\u5176\u5b9a\u4e49\u4f4d\u4e8e": [], "xuance_torch": [], "py\u548c": [], "xuance_m": [], "py\u4e2d": [], "\u5b9e\u4f8b\u5316\u8be5\u7c7b\u9700\u8981\u6307\u5b9a\u8f93\u5165\u5c3a\u5bf8": [], "input_shap": [133, 134, 135, 156], "\u6ee4\u6ce2\u65b9\u6cd5": [], "\u6838\u5927\u5c0f": [], "kernel_s": 133, "\u6b65\u957f": [], "\u5f52\u4e00\u5316\u65b9\u6cd5": [], "\u6fc0\u6d3b\u51fd\u6570": [], "\u521d\u59cb\u5316\u65b9\u6cd5": [], "initi": [133, 134, 135, 156], "\u5728pytorch\u4e0b\u5b9e\u73b0\u8fd8\u9700\u6307\u5b9a\u8bbe\u5907\u7c7b\u578b": [], "\u4ee5\u786e\u5b9a\u6a21\u578b\u5728cpu\u4e0a\u8fd0\u884c\u8fd8\u662fgpu": [], "convolv": 133, "two": [84, 133, 135, 154, 155], "produc": 133, "_create_network": [133, 134, 135], "netowrk": [133, 134, 135], "forward": [133, 134, 135], "featur": [133, 134, 135], "ac_cnn_atari": 133, "fc_hidden_s": [133, 135], "final": [133, 154, 156], "fulli": [133, 135], "connect": [133, 135], "_init_lay": 133, "sqrt": 133, "bia": 133, "bias": 133, "sing": 133, "orthogon": 133, "initil": 133, "defualt": 133, "moduletyp": [133, 134, 135], "callabl": [133, 134, 135], "zip": 133, "extend": [133, 134, 135], "adaptivemaxpool2d": 133, "flatten": 133, "sequenti": [133, 134, 135], "255": 133, "tensor_observ": [133, 134], "orthogonal_": [133, 156], "constant_": 133, "prod": 133, "h": [133, 134, 135], "mlp_block": [133, 134, 135], "\u591a\u5c42\u611f\u77e5\u5668\u662f\u4e00\u79cd\u6700\u7b80\u5355\u7684\u6df1\u5c42\u795e\u7ecf\u7f51\u7edc\u6a21\u578b": [], "\u7528\u4e8e\u5904\u7406\u5411\u91cf\u8f93\u5165": [], "\u7528\u6237\u53ef\u6839\u636e\u5404\u81ea\u9700\u8981\u5b9e\u4f8b\u5316\u591a\u5c42\u611f\u77e5\u5668\u6a21\u5757": [], "\u7c7b\u540d\u79f0\u4e3amlp_block": [], "\u5b9e\u4f8b\u5316\u8be5\u7c7b\u9700\u6307\u5b9a\u8f93\u5165\u7ef4\u5ea6\u5927\u5c0f": [], "input_dim": [134, 135], "\u8f93\u51fa\u7ef4\u5ea6\u5927\u5c0f": [], "output_dim": [134, 135], "\u6fc0\u6d3b\u51fd\u6570\u9009\u62e9": [], "basic_ident": 134, "basic_mlp": [134, 156], "assert": 134, "hidden_s": [134, 135, 156], "\u5faa\u73af\u795e\u7ecf\u7f51\u7edc\u4e3b\u8981\u7528\u4e8e\u5904\u7406\u65f6\u5e8f\u4fe1\u53f7\u4fe1\u606f": [], "\u63d0\u53d6\u51fa\u5f53\u524d\u65f6\u5e8f\u4fe1\u53f7\u7684\u7279\u5f81\u5411\u91cf": [], "\u6839\u636e\u4f7f\u7528\u573a\u666f\u5dee\u5f02": [], "\u672c\u8f6f\u4ef6\u63d0\u4f9b\u4e24\u79cd\u5faa\u73af\u795e\u7ecf\u7f51\u8def\u6a21\u5757": [], "gru_block\u548clstm_block": [], "\u5176\u5b9a\u4e49\u5747\u4f4d\u4e8e": [], "\u526a\u679d\u65b9\u6cd5": [], "droupout": [], "\u540c\u6837\u5730": [], "basic_rnn": 135, "which": [84, 134, 135, 154, 156], "befor": [135, 155], "recurrent_hidden_s": 135, "c": 135, "last": 135, "lstm": 135, "init_hidden": 135, "batch": 135, "init_hidden_item": 135, "slice": 135, "given": 135, "get_hidden_item": 135, "use_norm": 135, "input_norm": 135, "norm_rnn": 135, "mlp_layer": 135, "rnn_layer": 135, "lstm_block": 135, "gru_block": 135, "mlp_output": 135, "flatten_paramet": 135, "hn": 135, "cn": 135, "rnn_cell": 135, "cell_stat": 135, "zeros_lik": 135, "runner_bas": 136, "set": [84, 136, 156], "runner_drl": 136, "runner_pettingzoo": 136, "runner_sc2": 136, "runner_footbal": 136, "runner_mag": 136, "reform": 143, "block": [133, 143], "oper": [143, 156], "some": [143, 155, 156], "norm": 143, "ant": [152, 156], "halfcheetah": 152, "hopper": 152, "walker2d": 152, "swimmer": 152, "humanoid": 152, "reacher": 152, "ipendulum": 152, "idpendulum": 152, "1472": 152, "10093": 152, "3434": 152, "9": 152, "2443": 152, "67": 152, "9359": 152, "tianshou": 152, "990": 152, "11718": 152, "2197": 152, "1400": 152, "144": 152, "177": 152, "8364": 152, "1005": 152, "3305": 152, "2020": 152, "1843": 152, "9355": 152, "spinningup": 152, "840": 152, "11000": 152, "1800": 152, "1950": 152, "137": 152, "4822": 152, "10718": 152, "3492": 152, "4307": 152, "59": 152, "547": 152, "88": 152, "07": 152, "9358": 152, "5116": 152, "10201": 152, "3472": 152, "3982": 152, "104": 152, "5189": 152, "9349": 152, "4372": 152, "9637": 152, "3564": 152, "4682": 152, "9337": 152, "3800": 152, "9750": 152, "2860": 152, "4000": 152, "78": 152, "1420": 152, "2674": 152, "825": 152, "970": 152, "51": 152, "240": 152, "11": 152, "9357": 152, "3485": 152, "1829": 152, "1253": 152, "1091": 152, "36": 152, "1726": 152, "9257": 152, "900": 152, "850": 152, "31": 152, "24": 152, "8100": 152, "2810": 152, "4628": 152, "3450": 152, "4318": 152, "108": 152, "705": 152, "3258": 152, "5783": 152, "2609": 152, "3588": 152, "66": 152, "787": 152, "9231": 152, "2330": 152, "3460": 152, "8000": 152, "650": 152, "1670": 152, "1850": 152, "1230": 152, "120": 152, "In": [154, 156], "easi": [154, 155, 157], "first": [154, 156], "need": [133, 134, 135, 154], "built": 154, "toi": 157, "v0": 154, "after": [154, 155, 156], "code": [84, 154, 155, 156], "support": [84, 154], "both": 154, "cooper": 154, "competit": 154, "similali": 154, "simple_spread": [], "For": 154, "competitv": 154, "divid": [154, 156], "more": 154, "side": 154, "demo": 154, "simple_push": 154, "thi": [84, 133, 134, 135, 154, 155, 156, 157], "adversary_0": 154, "agent_0": 154, "adversari": 154, "runner_test": [], "what": [], "happen": [], "automat": [], "gener": [], "result": [154, 156], "abl": [], "see": [], "command": [154, 155, 156], "librari": 155, "linux": 155, "window": 155, "maco": 155, "eulero": 155, "anaconda": 155, "prepar": [155, 156], "python": [155, 156], "conda": 155, "suggest": 155, "xpolici": 155, "pip": 155, "doe": 155, "includ": [155, 156], "depend": [135, 154, 155], "toolbox": [155, 156, 157], "tensorflow2": 155, "all": [155, 156], "extra": 155, "packag": [155, 156], "manual": 155, "further": [155, 156], "usag": [135, 155, 157], "help": 156, "instal": 157, "tutori": 156, "take": [133, 154, 156], "exampl": [], "necessari": 156, "here": 156, "we": [156, 157], "show": 156, "dqn_cartpol": [], "an": [156, 157], "ensembl": 157, "call": [156, 157], "xuan": 157, "ce": 157, "\u7384\u7b56": 157, "chines": 157, "\u7384": 157, "incred": 157, "magic": 157, "\u7b56": 157, "sensit": 157, "tune": 157, "vari": 157, "perform": [154, 156, 157], "differ": 157, "suffer": 157, "unstabl": 157, "therefor": 157, "sometim": 157, "seem": 157, "elus": 157, "give": 157, "thorough": 157, "qualiti": 157, "understand": [156, 157], "hope": 157, "hint": 157, "expect": 157, "compat": 157, "multipl": [84, 157], "realli": 157, "becom": 157, "zoo": 157, "THe": 157, "ha": [155, 157], "been": [155, 157], "github": [154, 156, 157], "openi": 157, "http": [154, 155, 156, 157], "com": [154, 155, 156, 157], "agi": [155, 156, 157], "brain": [155, 156, 157], "git": [154, 155, 157], "quick": 157, "profession": 157, "magent": 157, "search": [156, 157], "simple_spread_v3": 154, "simple_push_v3": 154, "complet": 154, "design": 154, "abov": [154, 155, 156], "benchmark": [154, 156], "instead": 154, "obtain": [154, 156], "folder": [84, 154], "root": 154, "actual": 154, "configur": [154, 156], "w": 154, "b": 154, "account": 154, "offici": 154, "instruct": [154, 156], "usernam": 154, "its": [154, 155], "local": 154, "deploy": 154, "refer": 154, "server": 154, "wai": 155, "them": 155, "altern": 155, "same": 155, "download": 155, "clone": 155, "cd": 155, "xuanc": [], "enter": 155, "runtim": 155, "Then": [155, 156], "error": 155, "warn": 155, "messag": 155, "displai": 155, "indic": 155, "successfulli": 155, "proce": 155, "previou": 156, "demonstr": 156, "how": 156, "order": 156, "better": 156, "facilit": 156, "develop": 156, "own": [134, 156], "section": 156, "detail": 156, "introduct": 156, "api": 156, "bottom": 156, "your_user_nam": 156, "dummy_gym": 156, "representation_hidden_s": 156, "256": 156, "actor_hidden_s": 156, "critic_hidden_s": 156, "leakyrelu": 156, "79811": 156, "0004": 156, "25": 156, "001": 156, "95": 156, "5000": 156, "mainli": [133, 135, 156], "read": 156, "creation": 156, "ppo_mujoco": 156, "py": [84, 133, 134, 135, 156], "write": 156, "consol": 156, "parse_arg": 156, "line": 156, "parser": 156, "argumentpars": 156, "add_argu": 156, "invertedpendulum": 156, "v4": 156, "ppo_mujoco_config": 156, "get_argu": 156, "__name__": 156, "__main__": 156, "parser_arg": 156, "readabl": 156, "combin": 156, "alreadi": 156, "thei": [84, 133, 156], "pars": [], "r": [], "duplic": 156, "latter": 156, "overwrit": 156, "former": 156, "ultim": 156, "instanti": [133, 134, 135, 156], "definit": [84, 135, 156], "comment": 156, "deepcopi": 156, "set_se": 156, "activationfunct": 156, "gaussian_ac_polici": 156, "ppoclip_ag": 156, "args_test": 156, "epoch": 156, "num_epoch": 156, "test_scor": 156, "best_scores_info": 156, "averag": 156, "standard": 156, "deviat": 156, "i_epoch": 156, "begin": 156, "than": 156, "histori": 156, "best_model": 156, "pth": 156, "without": 156, "n_train_step": 156, "final_train_model": 156, "python_mujoco": 156, "visit": 156, "extract": [133, 135], "usual": 133, "matric": 133, "dimension": 133, "defin": [133, 134], "when": [133, 134, 135], "determin": [133, 134, 135], "whether": [133, 134, 135], "one": 134, "simplest": 134, "dimens": [134, 135], "signal": 135, "Their": 135, "found": [84, 135], "respect": [84, 135], "prune": 135, "similarli": 135, "raw": [], "html": [], "br": [], "hr": [], "navig": 84, "improv": 84, "effici": 84, "up": 84, "involv": 84, "simultan": 84, "On": 84, "top": 84, "dummyvecenv": 84}, "objects": {"xuance.mindspore.agents.agents_marl": [[59, 0, 1, "", "MARLAgent"]], "xuance.mindsporetensorflow.agent.agent": [[40, 0, 1, "", "Agent"]], "xuance.tensorflow.agents.agents_marl": [[59, 0, 1, "", "MARLAgent"]], "xuance.tensorflowtensorflow.agent.agent": [[40, 0, 1, "", "Agent"]], "xuance.torch.agent.mutli_agent_rl.coma_agents": [[60, 0, 1, "", "COMA_Agents"]], "xuance.torch.agent.mutli_agent_rl.coma_agents.COMA_Agents": [[60, 1, 1, "", "act"], [60, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.dcg_agents": [[61, 0, 1, "", "DCG_Agents"]], "xuance.torch.agent.mutli_agent_rl.dcg_agents.DCG_Agents": [[61, 1, 1, "", "act"], [61, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.iddpg_agents": [[62, 0, 1, "", "IDDPG_Agents"]], "xuance.torch.agent.mutli_agent_rl.iddpg_agents.IDDPG_Agents": [[62, 1, 1, "", "act"], [62, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.ippo_agents": [[63, 0, 1, "", "IPPO_Agents"]], "xuance.torch.agent.mutli_agent_rl.iql_agents": [[64, 0, 1, "", "IQL_Agents"]], "xuance.torch.agent.mutli_agent_rl.iql_agents.IQL_Agents": [[64, 1, 1, "", "act"], [64, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.isac_agents": [[65, 0, 1, "", "ISAC_Agents"]], "xuance.torch.agent.mutli_agent_rl.isac_agents.ISAC_Agents": [[65, 1, 1, "", "act"], [65, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.maddpg_agents": [[66, 0, 1, "", "MADDPG_Agents"]], "xuance.torch.agent.mutli_agent_rl.maddpg_agents.MADDPG_Agents": [[66, 1, 1, "", "act"], [66, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.mappo_agents": [[67, 0, 1, "", "MAPPO_Agents"]], "xuance.torch.agent.mutli_agent_rl.mappo_agents.MAPPO_Agents": [[67, 1, 1, "", "act"], [67, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.masac_agents": [[68, 0, 1, "", "MASAC_Agents"]], "xuance.torch.agent.mutli_agent_rl.masac_agents.MASAC_Agents": [[68, 1, 1, "", "act"], [68, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.matd3_agents": [[69, 0, 1, "", "MATD3_Agents"]], "xuance.torch.agent.mutli_agent_rl.matd3_agents.MATD3_Agents": [[69, 1, 1, "", "act"], [69, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.mfq_agents": [[71, 0, 1, "", "MFQ_Agents"]], "xuance.torch.agent.mutli_agent_rl.mfq_agents.MFQ_Agents": [[71, 1, 1, "", "act"], [71, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.qmix_agents": [[72, 0, 1, "", "QMIX_Agents"]], "xuance.torch.agent.mutli_agent_rl.qmix_agents.QMIX_Agents": [[72, 1, 1, "", "act"], [72, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.qtran_agents": [[73, 0, 1, "", "QTRAN_Agents"]], "xuance.torch.agent.mutli_agent_rl.qtran_agents.QTRAN_Agents": [[73, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.vdn_agents": [[75, 0, 1, "", "VDN_Agents"]], "xuance.torch.agent.mutli_agent_rl.vdn_agents.VDN_Agents": [[75, 1, 1, "", "act"], [75, 1, 1, "", "train"]], "xuance.torch.agent.mutli_agent_rl.wqmix_agents": [[76, 0, 1, "", "WQMIX_Agents"]], "xuance.torch.agent.mutli_agent_rl.wqmix_agents.WQMIX_Agents": [[76, 1, 1, "", "act"], [76, 1, 1, "", "train"]], "xuance.torch.agent.policy_gradient.a2c_agent": [[39, 0, 1, "", "A2C_Agent"]], "xuance.torch.agent.policy_gradient.a2c_agent.A2C_Agent": [[39, 1, 1, "", "_action"], [39, 1, 1, "", "test"], [39, 1, 1, "", "train"]], "xuance.torch.agent.policy_gradient.ddpg_agent": [[42, 0, 1, "", "DDPG_Agent"]], "xuance.torch.agent.policy_gradient.ddpg_agent.DDPG_Agent": [[42, 1, 1, "", "_action"], [42, 1, 1, "", "test"], [42, 1, 1, "", "train"]], "xuance.torch.agent.policy_gradient.mpdqn_agent": [[46, 0, 1, "", "MPDQN_Agent"]], "xuance.torch.agent.policy_gradient.mpdqn_agent.MPDQN_Agent": [[46, 1, 1, "", "_action"], [46, 1, 1, "", "pad_action"], [46, 1, 1, "", "test"], [46, 1, 1, "", "train"]], "xuance.torch.agent.policy_gradient.pdqn_agent": [[48, 0, 1, "", "PDQN_Agent"]], "xuance.torch.agent.policy_gradient.pdqn_agent.PDQN_Agent": [[48, 1, 1, "", "_action"], [48, 1, 1, "", "pad_action"], [48, 1, 1, "", "test"], [48, 1, 1, "", "train"]], "xuance.torch.agent.policy_gradient.pg_agent": [[50, 0, 1, "", "PG_Agent"]], "xuance.torch.agent.policy_gradient.pg_agent.PG_Agent": [[50, 1, 1, "", "_action"], [50, 1, 1, "", "test"], [50, 1, 1, "", "train"]], "xuance.torch.agent.policy_gradient.ppg_agent": [[51, 0, 1, "", "PPG_Agent"]], "xuance.torch.agent.policy_gradient.ppg_agent.PPG_Agent": [[51, 1, 1, "", "_action"], [51, 1, 1, "", "test"], [51, 1, 1, "", "train"]], "xuance.torch.agent.policy_gradient.ppoclip_agent": [[52, 0, 1, "", "PPOCLIP_Agent"]], "xuance.torch.agent.policy_gradient.ppoclip_agent.PPOCLIP_Agent": [[52, 1, 1, "", "_action"], [52, 1, 1, "", "test"], [52, 1, 1, "", "train"]], "xuance.torch.agent.policy_gradient.ppokl_agent": [[53, 0, 1, "", "PPOKL_Agent"]], "xuance.torch.agent.policy_gradient.ppokl_agent.PPOKL_Agent": [[53, 1, 1, "", "_action"], [53, 1, 1, "", "test"], [53, 1, 1, "", "train"]], "xuance.torch.agent.policy_gradient.sac_agent": [[55, 0, 1, "", "SAC_Agent"]], "xuance.torch.agent.policy_gradient.sac_agent.SAC_Agent": [[55, 1, 1, "", "_action"], [55, 1, 1, "", "test"], [55, 1, 1, "", "train"]], "xuance.torch.agent.policy_gradient.sacdis_agent": [[56, 0, 1, "", "SACDIS_Agent"]], "xuance.torch.agent.policy_gradient.sacdis_agent.SACDIS_Agent": [[56, 1, 1, "", "_action"], [56, 1, 1, "", "test"], [56, 1, 1, "", "train"]], "xuance.torch.agent.policy_gradient.spdqn_agent": [[57, 0, 1, "", "SPDQN_Agent"]], "xuance.torch.agent.policy_gradient.spdqn_agent.SPDQN_Agent": [[57, 1, 1, "", "_action"], [57, 1, 1, "", "pad_action"], [57, 1, 1, "", "test"], [57, 1, 1, "", "train"]], "xuance.torch.agent.policy_gradient.td3_agent": [[58, 0, 1, "", "TD3_Agent"]], "xuance.torch.agent.policy_gradient.td3_agent.TD3_Agent": [[58, 1, 1, "", "_action"], [58, 1, 1, "", "test"], [58, 1, 1, "", "train"]], "xuance.torch.agent.qlearning_family.c51_agent": [[41, 0, 1, "", "C51_Agent"]], "xuance.torch.agent.qlearning_family.c51_agent.C51_Agent": [[41, 1, 1, "", "_action"], [41, 1, 1, "", "test"], [41, 1, 1, "", "train"]], "xuance.torch.agent.qlearning_family.ddqn_agent": [[43, 0, 1, "", "DDQN_Agent"]], "xuance.torch.agent.qlearning_family.ddqn_agent.DDQN_Agent": [[43, 1, 1, "", "_action"], [43, 1, 1, "", "test"], [43, 1, 1, "", "train"]], "xuance.torch.agent.qlearning_family.dqn_agent": [[44, 0, 1, "", "DQN_Agent"]], "xuance.torch.agent.qlearning_family.dqn_agent.DQN_Agent": [[44, 1, 1, "", "_action"], [44, 1, 1, "", "test"], [44, 1, 1, "", "train"]], "xuance.torch.agent.qlearning_family.dueldqn_agent": [[45, 0, 1, "", "DuelDQN_Agent"]], "xuance.torch.agent.qlearning_family.dueldqn_agent.DuelDQN_Agent": [[45, 1, 1, "", "_action"], [45, 1, 1, "", "test"], [45, 1, 1, "", "train"]], "xuance.torch.agent.qlearning_family.noisydqn_agent": [[47, 0, 1, "", "NoisyDQN_Agent"]], "xuance.torch.agent.qlearning_family.noisydqn_agent.NoisyDQN_Agent": [[47, 1, 1, "", "_action"], [47, 1, 1, "", "test"], [47, 1, 1, "", "train"]], "xuance.torch.agent.qlearning_family.perdqn_agent": [[49, 0, 1, "", "PerDQN_Agent"]], "xuance.torch.agent.qlearning_family.perdqn_agent.PerDQN_Agent": [[49, 1, 1, "", "_action"], [49, 1, 1, "", "test"], [49, 1, 1, "", "train"]], "xuance.torch.agent.qlearning_family.qrdqn_agent": [[54, 0, 1, "", "QRDQN_Agent"]], "xuance.torch.agent.qlearning_family.qrdqn_agent.QRDQN_Agent": [[54, 1, 1, "", "_action"], [54, 1, 1, "", "test"], [54, 1, 1, "", "train"]], "xuance.torch.agents.agent": [[40, 0, 1, "", "Agent"]], "xuance.torch.agents.agent.Agent": [[40, 1, 1, "", "_action"], [40, 1, 1, "", "_process_observation"], [40, 1, 1, "", "_process_reward"], [40, 1, 1, "", "finish"], [40, 1, 1, "", "load_model"], [40, 1, 1, "", "log_infos"], [40, 1, 1, "", "log_videos"], [40, 1, 1, "", "save_model"], [40, 1, 1, "", "test"], [40, 1, 1, "", "train"]], "xuance.torch.agents.agents_marl": [[59, 0, 1, "", "MARLAgent"], [59, 0, 1, "", "RandomAgents"], [59, 0, 1, "", "linear_decay_or_increase"]], "xuance.torch.agents.agents_marl.MARLAgent": [[59, 1, 1, "", "act"], [59, 1, 1, "", "load_model"], [59, 1, 1, "", "save_model"], [59, 1, 1, "", "train"]], "xuance.torch.agents.agents_marl.RandomAgents": [[59, 1, 1, "", "act"]], "xuance.torch.agents.agents_marl.linear_decay_or_increase": [[59, 1, 1, "", "update"]], "xuance.torch.learners.learner": [[105, 0, 1, "", "Learner"]], "xuance.torch.learners.learner.Learner": [[105, 1, 1, "", "load_model"], [105, 1, 1, "", "save_model"], [105, 1, 1, "", "update"]], "xuance.torch.representations.cnn": [[133, 0, 1, "", "AC_CNN_Atari"], [133, 0, 1, "", "Basic_CNN"]], "xuance.torch.representations.cnn.AC_CNN_Atari": [[133, 1, 1, "", "_create_network"], [133, 1, 1, "", "_init_layer"], [133, 1, 1, "", "forward"]], "xuance.torch.representations.cnn.Basic_CNN": [[133, 1, 1, "", "_create_network"], [133, 1, 1, "", "forward"]], "xuance.torch.representations.mlp": [[134, 0, 1, "", "Basic_Identical"], [134, 0, 1, "", "Basic_MLP"]], "xuance.torch.representations.mlp.Basic_Identical": [[134, 1, 1, "", "forward"]], "xuance.torch.representations.mlp.Basic_MLP": [[134, 1, 1, "", "_create_network"], [134, 1, 1, "", "forward"]], "xuance.torch.representations.rnn": [[135, 0, 1, "", "Basic_RNN"]], "xuance.torch.representations.rnn.Basic_RNN": [[135, 1, 1, "", "_create_network"], [135, 1, 1, "", "forward"], [135, 1, 1, "", "get_hidden_item"], [135, 1, 1, "", "init_hidden"], [135, 1, 1, "", "init_hidden_item"]]}, "objtypes": {"0": "py:class", "1": "py:function"}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"]}, "titleterms": {"a2c": 0, "advantag": 0, "actor": [0, 14, 15], "critic": [0, 14, 15], "c51": 1, "ddpg": 2, "deep": [2, 3, 19], "determinist": [2, 127, 128], "polici": [2, 12, 18, 123], "gradient": [2, 18], "ddqn": 3, "doubl": 3, "q": [3, 25], "network": [3, 36, 146], "dqn": [4, 6, 8, 10], "algorithm": [4, 5, 19, 20, 157], "descript": [4, 5], "drqn": 5, "duel": 6, "mpdqn": 7, "noisi": 8, "pdqn": 9, "per": 10, "ppg": 11, "ppo": 12, "proxim": 12, "optim": 12, "qrdqn": 13, "soft": [14, 15], "spdqn": 16, "td3": 17, "vanilla": 18, "reinforc": [19, 20], "learn": [19, 20, 25], "includ": 84, "multi": 20, "agent": [20, 38, 40], "coma": 21, "dcg": 22, "iddpg": 23, "iql": 25, "independ": 25, "isac": 26, "maddpg": 27, "mappo": 28, "masac": 29, "matd3": 30, "mfac": [31, 70], "mfq": 32, "qmix": [33, 37], "qtran": 34, "vdac": [35, 74], "vdn": 36, "valu": 36, "decomposit": 36, "weight": 37, "a2c_ag": 39, "\u6e90\u7801": [], "c51_agent": 41, "ddpg_agent": 42, "ddqn_agent": 43, "dqn_agent": 44, "dueldqn_ag": 45, "mpdqn_agent": 46, "noisydqn_ag": 47, "pdqn_agent": 48, "perdqn_ag": 49, "pg_agent": 50, "ppg_agent": 51, "ppoclip_ag": 52, "ppokl_ag": 53, "qrdqn_agent": 54, "sac_ag": 55, "sacdis_ag": 56, "spdqn_agent": 57, "td3_agent": 58, "marlag": 59, "coma_ag": 60, "dcg_agent": 61, "iddpg_ag": 62, "ippo_ag": 63, "iql_ag": 64, "isac_ag": 65, "maddpg_ag": 66, "mappo_ag": 67, "masac_ag": 68, "matd3_ag": 69, "\u7b97\u6cd5\u63cf\u8ff0": [], "\u7b97\u6cd5\u51fa\u5904": [], "mfq_agent": 71, "qmix_ag": 72, "qtran_ag": 73, "vdn_agent": 75, "wqmix_ag": 76, "common": [77, 78], "tool": [78, 82], "memori": [79, 80], "marl": [20, 80, 125, 128, 130, 154], "segment": 81, "tree": 81, "statist": 82, "config": [83, 156], "\u57fa\u7840\u53c2\u6570\u914d\u7f6e": 83, "\u7b97\u6cd5\u53c2\u6570\u914d\u7f6e": 83, "\u81ea\u5b9a\u4e49\u53c2\u6570\u914d\u7f6e": 83, "environ": [84, 149, 150, 151, 153], "custom": 84, "\u5411\u91cf\u5316\u4eff\u771f\u73af\u5883": [], "learner": [85, 105], "a2c_learn": 86, "c51_learner": 87, "ddpg_learner": 88, "ddqn_learner": 89, "dqn_learner": 90, "dueldqn_learn": 91, "mpdqn_learner": 92, "noisydqn_learn": 93, "pdqn_learner": 94, "perdqn_learn": 95, "pg_learner": 96, "ppg_learner": 97, "ppoclip_learn": 98, "ppokl_learn": 99, "qrdqn_learner": 100, "sac_learn": 101, "sacdis_learn": 102, "spdqn_learner": 103, "td3_learner": 104, "coma_learn": 106, "dcg_learner": 107, "iddpg_learn": 108, "ippo_learn": 109, "iql_learn": 110, "isac_learn": 111, "maddpg_learn": 112, "mappo_learn": 113, "masac_learn": 114, "matd3_learn": 115, "mfac_learn": 116, "mfq_learner": 117, "qmix_learn": 118, "qtran_learn": 119, "vdac_learn": 120, "vdn_learner": 121, "wqmix_learn": 122, "categor": [124, 125], "coordin": 126, "graph": 126, "gaussian": [129, 130], "mixier": 131, "represent": 132, "cnn": 133, "base": [133, 134, 135], "mlp": 134, "rnn": 135, "runner": 136, "runner_bas": 137, "runner_drl": 138, "runner_footbal": 139, "runner_mag": 140, "runner_pettingzoo": 141, "runner_sc2": 142, "util": 143, "distribut": 144, "input": 145, "reform": 145, "neural": 146, "layer": 146, "oper": 147, "valuenorm": 148, "atari": 149, "benchmark": [149, 150, 151, 152, 153, 157], "\u73af\u5883\u4ecb\u7ecd": [], "magent": 150, "mpe": 151, "mujoco": 152, "scenario": 152, "result": 152, "toi": 153, "quick": 154, "start": 154, "run": [154, 156], "drl": [19, 154], "an": 154, "test": [154, 155], "logger": 154, "instal": 155, "profession": 156, "usag": 156, "step": 156, "1": 156, "creat": 156, "file": 156, "2": 156, "build": [], "3": 156, "4": [], "5": [], "select": [], "6": [], "7": [], "8": [], "train": [], "model": 156, "9": [], "10": [], "visual": [], "infom": [], "welcom": 157, "xuanpolici": 157, "": 157, "document": 157, "how": 157, "us": 157, "api": 157, "indic": 157, "tabl": 157, "exampl": [154, 156], "via": 155, "pypi": 155, "from": 155, "github": 155, "repositori": 155, "whether": 155, "wa": 155, "success": 155, "method": [], "get": 156, "attribut": 156, "defin": 156, "sourc": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 133, 134, 135], "code": [39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 75, 76, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 133, 134, 135], "discret": 15, "action": 15, "space": 15, "ippo": 24, "vector": 84}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"A2C: Advantage Actor-Critic": [[0, "a2c-advantage-actor-critic"]], "C51": [[1, "c51"]], "DDPG: Deep Deterministic Policy Gradient": [[2, "ddpg-deep-deterministic-policy-gradient"]], "DDQN: Double Deep Q-Networks": [[3, "ddqn-double-deep-q-networks"]], "DQN": [[4, "dqn"]], "Algorithm description": [[4, "algorithm-description"], [5, "algorithm-description"]], "DRQN": [[5, "drqn"]], "Duel DQN": [[6, "duel-dqn"]], "MPDQN": [[7, "mpdqn"]], "Noisy DQN": [[8, "noisy-dqn"]], "PDQN": [[9, "pdqn"]], "Per DQN": [[10, "per-dqn"]], "PPG": [[11, "ppg"]], "PPO: Proximal Policy Optimization": [[12, "ppo-proximal-policy-optimization"]], "QRDQN": [[13, "qrdqn"]], "Soft Actor-Critic": [[14, "soft-actor-critic"]], "SPDQN": [[16, "spdqn"]], "TD3": [[17, "td3"]], "Vanilla Policy Gradient": [[18, "vanilla-policy-gradient"]], "COMA": [[21, "coma"]], "DCG": [[22, "dcg"]], "IDDPG": [[23, "iddpg"]], "IQL: Independent Q-Learning": [[25, "iql-independent-q-learning"]], "ISAC": [[26, "isac"]], "MADDPG": [[27, "maddpg"]], "MAPPO": [[28, "mappo"]], "MASAC": [[29, "masac"]], "MATD3": [[30, "matd3"]], "MFAC": [[31, "mfac"], [70, "mfac"]], "MFQ": [[32, "mfq"]], "QMIX": [[33, "qmix"]], "QTRAN": [[34, "qtran"]], "VDAC": [[35, "vdac"], [74, "vdac"]], "VDN: Value Decomposition Networks": [[36, "vdn-value-decomposition-networks"]], "Weighted QMIX": [[37, "weighted-qmix"]], "Agents": [[38, "agents"]], "Common": [[77, "common"]], "Common Tools": [[78, "common-tools"]], "Memory": [[79, "memory"]], "Memory for MARL": [[80, "memory-for-marl"]], "Segment Tree": [[81, "segment-tree"]], "Statistic Tools": [[82, "statistic-tools"]], "Learners": [[85, "learners"]], "Policies": [[123, "policies"]], "Categorical": [[124, "categorical"]], "Categorical-MARL": [[125, "categorical-marl"]], "Coordination-Graph": [[126, "coordination-graph"]], "Deterministic": [[127, "deterministic"]], "Deterministic-MARL": [[128, "deterministic-marl"]], "Gaussian": [[129, "gaussian"]], "Gaussian-MARL": [[130, "gaussian-marl"]], "Mixiers": [[131, "mixiers"]], "Representations": [[132, "representations"]], "Runners": [[136, "runners"]], "Runner_Base": [[137, "runner-base"]], "Runner_DRL": [[138, "runner-drl"]], "Runner_Football": [[139, "runner-football"]], "Runner_MAgent": [[140, "runner-magent"]], "Runner_Pettingzoo": [[141, "runner-pettingzoo"]], "Runner_SC2": [[142, "runner-sc2"]], "Utils": [[143, "utils"]], "Distributions": [[144, "distributions"]], "Input Reformation": [[145, "input-reformation"]], "Neural Network Layers": [[146, "neural-network-layers"]], "Operations": [[147, "operations"]], "ValueNorm": [[148, "valuenorm"]], "MuJoCo benchmarks": [[152, "mujoco-benchmarks"]], "Scenarios": [[152, "scenarios"]], "Results": [[152, "results"]], "Welcome to XuanCe\u2019s documentation!": [[157, "welcome-to-xuance-s-documentation"]], "How to use:": [[157, null]], "API:": [[157, null]], "Benchmarks": [[157, null]], "Algorithms:": [[157, null]], "Indices and tables": [[157, "indices-and-tables"]], "Configs": [[83, "configs"]], "\u57fa\u7840\u53c2\u6570\u914d\u7f6e": [[83, "id1"]], "\u7b97\u6cd5\u53c2\u6570\u914d\u7f6e": [[83, "id2"]], "\u81ea\u5b9a\u4e49\u53c2\u6570\u914d\u7f6e": [[83, "id3"]], "A2C_Agent": [[39, "a2c-agent"]], "Source Code": [[39, "source-code"], [40, "source-code"], [41, "source-code"], [42, "source-code"], [43, "source-code"], [44, "source-code"], [45, "source-code"], [46, "source-code"], [47, "source-code"], [48, "source-code"], [49, "source-code"], [50, "source-code"], [51, "source-code"], [52, "source-code"], [53, "source-code"], [54, "source-code"], [55, "source-code"], [56, "source-code"], [57, "source-code"], [58, "source-code"], [59, "source-code"], [60, "source-code"], [61, "source-code"], [62, "source-code"], [63, "source-code"], [64, "source-code"], [65, "source-code"], [66, "source-code"], [67, "source-code"], [68, "source-code"], [69, "source-code"], [71, "source-code"], [72, "source-code"], [73, "source-code"], [75, "source-code"], [76, "source-code"], [86, "source-code"], [87, "source-code"], [88, "source-code"], [89, "source-code"], [90, "source-code"], [91, "source-code"], [92, "source-code"], [93, "source-code"], [94, "source-code"], [95, "source-code"], [96, "source-code"], [97, "source-code"], [98, "source-code"], [99, "source-code"], [100, "source-code"], [101, "source-code"], [102, "source-code"], [103, "source-code"], [104, "source-code"], [105, "source-code"], [106, "source-code"], [107, "source-code"], [108, "source-code"], [109, "source-code"], [110, "source-code"], [111, "source-code"], [112, "source-code"], [113, "source-code"], [114, "source-code"], [115, "source-code"], [116, "source-code"], [117, "source-code"], [118, "source-code"], [119, "source-code"], [120, "source-code"], [121, "source-code"], [122, "source-code"], [133, "source-code"], [134, "source-code"], [135, "source-code"]], "Agent": [[40, "agent"]], "C51_Agent": [[41, "c51-agent"]], "DDPG_Agent": [[42, "ddpg-agent"]], "DDQN_Agent": [[43, "ddqn-agent"]], "DQN_Agent": [[44, "dqn-agent"]], "DuelDQN_Agent": [[45, "dueldqn-agent"]], "MPDQN_Agent": [[46, "mpdqn-agent"]], "NoisyDQN_Agent": [[47, "noisydqn-agent"]], "PDQN_Agent": [[48, "pdqn-agent"]], "PerDQN_Agent": [[49, "perdqn-agent"]], "PG_Agent": [[50, "pg-agent"]], "PPG_Agent": [[51, "ppg-agent"]], "PPOCLIP_Agent": [[52, "ppoclip-agent"]], "PPOKL_Agent": [[53, "ppokl-agent"]], "QRDQN_Agent": [[54, "qrdqn-agent"]], "SAC_Agent": [[55, "sac-agent"]], "SACDIS_Agent": [[56, "sacdis-agent"]], "SPDQN_Agent": [[57, "spdqn-agent"]], "TD3_Agent": [[58, "td3-agent"]], "MARLAgent": [[59, "marlagent"]], "COMA_Agents": [[60, "coma-agents"]], "DCG_Agents": [[61, "dcg-agents"]], "IDDPG_Agents": [[62, "iddpg-agents"]], "IPPO_Agents": [[63, "ippo-agents"]], "IQL_Agents": [[64, "iql-agents"]], "ISAC_Agents": [[65, "isac-agents"]], "MADDPG_Agents": [[66, "maddpg-agents"]], "MAPPO_Agents": [[67, "mappo-agents"]], "MASAC_Agents": [[68, "masac-agents"]], "MATD3_Agents": [[69, "matd3-agents"]], "MFQ_Agents": [[71, "mfq-agents"]], "QMIX_Agents": [[72, "qmix-agents"]], "QTRAN_Agents": [[73, "qtran-agents"]], "VDN_Agents": [[75, "vdn-agents"]], "WQMIX_Agents": [[76, "wqmix-agents"]], "A2C_Learner": [[86, "a2c-learner"]], "C51_Learner": [[87, "c51-learner"]], "DDPG_Learner": [[88, "ddpg-learner"]], "DDQN_Learner": [[89, "ddqn-learner"]], "DQN_Learner": [[90, "dqn-learner"]], "DuelDQN_Learner": [[91, "dueldqn-learner"]], "MPDQN_Learner": [[92, "mpdqn-learner"]], "NoisyDQN_Learner": [[93, "noisydqn-learner"]], "PDQN_Learner": [[94, "pdqn-learner"]], "PerDQN_Learner": [[95, "perdqn-learner"]], "PG_Learner": [[96, "pg-learner"]], "PPG_Learner": [[97, "ppg-learner"]], "PPOCLIP_Learner": [[98, "ppoclip-learner"]], "PPOKL_Learner": [[99, "ppokl-learner"]], "QRDQN_Learner": [[100, "qrdqn-learner"]], "SAC_Learner": [[101, "sac-learner"]], "SACDIS_Learner": [[102, "sacdis-learner"]], "SPDQN_Learner": [[103, "spdqn-learner"]], "TD3_Learner": [[104, "td3-learner"]], "Learner": [[105, "learner"]], "COMA_Learner": [[106, "coma-learner"]], "DCG_Learner": [[107, "dcg-learner"]], "IDDPG_Learner": [[108, "iddpg-learner"]], "IPPO_Learner": [[109, "ippo-learner"]], "IQL_Learner": [[110, "iql-learner"]], "ISAC_Learner": [[111, "isac-learner"]], "MADDPG_Learner": [[112, "maddpg-learner"]], "MAPPO_Learner": [[113, "mappo-learner"]], "MASAC_Learner": [[114, "masac-learner"]], "MATD3_Learner": [[115, "matd3-learner"]], "MFAC_Learner": [[116, "mfac-learner"]], "MFQ_Learner": [[117, "mfq-learner"]], "QMIX_Learner": [[118, "qmix-learner"]], "QTRAN_Learner": [[119, "qtran-learner"]], "VDAC_Learner": [[120, "vdac-learner"]], "VDN_Learner": [[121, "vdn-learner"]], "WQMIX_Learner": [[122, "wqmix-learner"]], "CNN-based": [[133, "cnn-based"]], "MLP-based": [[134, "mlp-based"]], "Soft Actor-Critic for discrete action space": [[15, "soft-actor-critic-for-discrete-action-space"]], "Deep Reinforcement Learning": [[19, "deep-reinforcement-learning"]], "DRL Algorithms": [[19, null]], "Multi-Agent Reinforcement Learning": [[20, "multi-agent-reinforcement-learning"]], "MARL Algorithms": [[20, null]], "IPPO": [[24, "ippo"]], "Quick Start": [[154, "quick-start"]], "Run a DRL example": [[154, "run-a-drl-example"]], "Run an MARL example": [[154, "run-an-marl-example"]], "Test": [[154, "test"]], "Logger": [[154, "logger"]], "Installation": [[155, "installation"]], "Install via PyPI": [[155, "install-via-pypi"]], "Install from GitHub repository": [[155, "install-from-github-repository"]], "Testing whether the installation was successful": [[155, "testing-whether-the-installation-was-successful"]], "Professional Usage": [[156, "professional-usage"]], "Step 1: Create config file": [[156, "step-1-create-config-file"]], "Step 2: Get the attributes of the example": [[156, "step-2-get-the-attributes-of-the-example"]], "Step 3: Define run(), create and run the model": [[156, "step-3-define-run-create-and-run-the-model"]], "RNN-based": [[135, "rnn-based"]], "Environments": [[84, "environments"], [149, "environments"], [150, "environments"], [151, "environments"], [153, "environments"]], "Included Environments": [[84, "included-environments"]], "Customized Environments": [[84, "customized-environments"]], "Vectorize the Environment": [[84, "vectorize-the-environment"]], "Atari benchmarks": [[149, "atari-benchmarks"]], "Magent benchmarks": [[150, "magent-benchmarks"]], "MPE benchmarks": [[151, "mpe-benchmarks"]], "Toy benchmarks": [[153, "toy-benchmarks"]]}, "indexentries": {}}) \ No newline at end of file diff --git a/docs/source/conf.py b/docs/source/conf.py index 26d28cb29..b07070a9f 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -6,9 +6,9 @@ # -- Project information ----------------------------------------------------- # https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information -project = 'XuanPolicy' -copyright = '2023, XuanPolicy contributors' -author = 'XuanPolicy contributors' +project = 'XuanCe' +copyright = '2023, XuanCe contributors' +author = 'XuanCe contributors' release = 'v0.1.11' # -- General configuration --------------------------------------------------- diff --git a/docs/source/documents/api/agents/drl/a2c.rst b/docs/source/documents/api/agents/drl/a2c.rst index 104a6c7d7..65e154c60 100644 --- a/docs/source/documents/api/agents/drl/a2c.rst +++ b/docs/source/documents/api/agents/drl/a2c.rst @@ -8,12 +8,12 @@ A2C_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.policy_gradient.a2c_agent.A2C_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.policy_gradient.a2c_agent.A2C_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ A2C_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.policy_gradient.a2c_agent.A2C_Agent._action(obs) + xuance.torch.agent.policy_gradient.a2c_agent.A2C_Agent._action(obs) Calculate actions according to the observations. @@ -34,7 +34,7 @@ A2C_Agent :rtype: np.ndarray, np.ndarray .. py:function:: - xuanpolicy.torch.agent.policy_gradient.a2c_agent.A2C_Agent.train(train_steps) + xuance.torch.agent.policy_gradient.a2c_agent.A2C_Agent.train(train_steps) Train the A2C agent. @@ -42,7 +42,7 @@ A2C_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.policy_gradient.a2c_agent.A2C_Agent.test(env_fn, test_episodes) + xuance.torch.agent.policy_gradient.a2c_agent.A2C_Agent.test(env_fn, test_episodes) Test the trained model. @@ -79,7 +79,7 @@ Source Code import numpy as np - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class A2C_Agent(Agent): diff --git a/docs/source/documents/api/agents/drl/basic_drl_class.rst b/docs/source/documents/api/agents/drl/basic_drl_class.rst index 89f81a73e..c75571048 100644 --- a/docs/source/documents/api/agents/drl/basic_drl_class.rst +++ b/docs/source/documents/api/agents/drl/basic_drl_class.rst @@ -1,23 +1,23 @@ Agent ======================= -To create a new Agent, you should build a class inherit from ``xuanpolicy.torch.agents.agent.Agent`` , ``xuanpolicy.tensorflow.agents.agent.Agent``, or ``xuanpolicy.mindspore.agents.agent.Agent``. +To create a new Agent, you should build a class inherit from ``xuance.torch.agents.agent.Agent`` , ``xuance.tensorflow.agents.agent.Agent``, or ``xuance.mindspore.agents.agent.Agent``. **PyTorch:** .. py:class:: - xuanpolicy.torch.agents.agent.Agent(config, envs, policy, memory, learner, device, log_dir, model_dir) + xuance.torch.agents.agent.Agent(config, envs, policy, memory, learner, device, log_dir, model_dir) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param memory: Experice replay buffer. - :type memory: xuanpolicy.common.memory_tools.Buffer + :type memory: xuance.common.memory_tools.Buffer :param learner: The learner that updates parameters of policy. - :type learner: xuanpolicy.torch.learner.Learner + :type learner: xuance.torch.learner.Learner :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device :param log_dir: The directory of log file, default is "./logs/". @@ -25,14 +25,14 @@ To create a new Agent, you should build a class inherit from ``xuanpolicy.torch. :param model_dir: The directory of model file, default is "./models/". :type model_dir: str -.. py:function:: xuanpolicy.torch.agents.agent.Agent.save_model(model_name) +.. py:function:: xuance.torch.agents.agent.Agent.save_model(model_name) Save the model. :param model_name: The model's name to be saved. :type model_name: str -.. py:function:: xuanpolicy.torch.agents.agent.Agent.load_model(path, seed) +.. py:function:: xuance.torch.agents.agent.Agent.load_model(path, seed) Load a model by specifying the ``path`` and ``seed`` . @@ -41,7 +41,7 @@ To create a new Agent, you should build a class inherit from ``xuanpolicy.torch. :param seed: Select the seed that model was trained with if it exits. :type seed: int -.. py:function:: xuanpolicy.torch.agents.agent.Agent.log_infos(info, x_index) +.. py:function:: xuance.torch.agents.agent.Agent.log_infos(info, x_index) Visualize the training information via wandb or tensorboard. @@ -50,7 +50,7 @@ To create a new Agent, you should build a class inherit from ``xuanpolicy.torch. :param x_index: Current step. :type x_index: int -.. py:function:: xuanpolicy.torch.agents.agent.Agent.log_videos(info, fps x_index) +.. py:function:: xuance.torch.agents.agent.Agent.log_videos(info, fps x_index) Visualize the interaction between agent and environment by uploading the videos with wandb or tensorboard. @@ -61,7 +61,7 @@ To create a new Agent, you should build a class inherit from ``xuanpolicy.torch. :param x_index: Current step. :type x_index: int -.. py:function:: xuanpolicy.torch.agents.agent.Agent._process_observation(observations) +.. py:function:: xuance.torch.agents.agent.Agent._process_observation(observations) Normalize the original observations. @@ -70,7 +70,7 @@ To create a new Agent, you should build a class inherit from ``xuanpolicy.torch. :return: The normalized observations. :rtype: numpy.ndarray -.. py:function:: xuanpolicy.torch.agents.agent.Agent._process_reward(rewards) +.. py:function:: xuance.torch.agents.agent.Agent._process_reward(rewards) Normalize the original rewards. @@ -79,21 +79,21 @@ To create a new Agent, you should build a class inherit from ``xuanpolicy.torch. :return: The normalized observations rewards. :rtype: numpy.ndarray -.. py:function:: xuanpolicy.torch.agents.agent.Agent._action(observations) +.. py:function:: xuance.torch.agents.agent.Agent._action(observations) Get actions for executing according to the observations. :param observations: The original observations of agent. :type observations: numpy.ndarray -.. py:function:: xuanpolicy.torch.agents.agent.Agent.train(steps) +.. py:function:: xuance.torch.agents.agent.Agent.train(steps) Train the agents with ``steps`` steps. :param steps: The training steps. :type steps: int -.. py:function:: xuanpolicy.torch.agents.agent.Agent.test(env_fn, steps) +.. py:function:: xuance.torch.agents.agent.Agent.test(env_fn, steps) Test the agents. @@ -101,7 +101,7 @@ To create a new Agent, you should build a class inherit from ``xuanpolicy.torch. :param steps: The training steps. :type steps: int -.. py:function:: xuanpolicy.torch.agents.agent.Agent.finish() +.. py:function:: xuance.torch.agents.agent.Agent.finish() Finish the wandb or tensorboard. @@ -113,18 +113,18 @@ To create a new Agent, you should build a class inherit from ``xuanpolicy.torch. **TensorFlow:** .. py:class:: - xuanpolicy.tensorflowtensorflow.agent.agent.Agent(config, envs, policy, memory, learner, device, log_dir, model_dir) + xuance.tensorflowtensorflow.agent.agent.Agent(config, envs, policy, memory, learner, device, log_dir, model_dir) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param memory: Experice replay buffer. - :type memory: xuanpolicy.common.memory_tools.Buffer + :type memory: xuance.common.memory_tools.Buffer :param learner: The learner that updates parameters of policy. - :type learner: xuanpolicy.tensorflow.learner.Learner + :type learner: xuance.tensorflow.learner.Learner :param device: Choose CPU or GPU to train the model. :type device: str :param log_dir: The directory of log file, default is "./logs/". @@ -140,16 +140,16 @@ To create a new Agent, you should build a class inherit from ``xuanpolicy.torch. **MindSpore:** .. py:class:: - xuanpolicy.mindsporetensorflow.agent.agent.Agent(envs, policy, memory, learner, device, log_dir, model_dir) + xuance.mindsporetensorflow.agent.agent.Agent(envs, policy, memory, learner, device, log_dir, model_dir) :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param memory: Experice replay buffer. - :type memory: xuanpolicy.common.memory_tools.Buffer + :type memory: xuance.common.memory_tools.Buffer :param learner: The learner that updates parameters of policy. - :type learner: xuanpolicy.mindspore.learner.Learner + :type learner: xuance.mindspore.learner.Learner :param device: Choose CPU or GPU to train the model. :type device: str :param log_dir: The directory of log file, default is "./logs/". diff --git a/docs/source/documents/api/agents/drl/c51.rst b/docs/source/documents/api/agents/drl/c51.rst index 883effd27..d1a1c5051 100644 --- a/docs/source/documents/api/agents/drl/c51.rst +++ b/docs/source/documents/api/agents/drl/c51.rst @@ -8,12 +8,12 @@ C51_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.qlearning_family.c51_agent.C51_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.qlearning_family.c51_agent.C51_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ C51_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.qlearning_family.c51_agent.C51_Agent._action(obs, egreedy) + xuance.torch.agent.qlearning_family.c51_agent.C51_Agent._action(obs, egreedy) Calculate actions according to the observations. @@ -36,7 +36,7 @@ C51_Agent :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.qlearning_family.c51_agent.C51_Agent.train(train_steps) + xuance.torch.agent.qlearning_family.c51_agent.C51_Agent.train(train_steps) Train the C51DQN agent. @@ -44,7 +44,7 @@ C51_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.qlearning_family.c51_agent.C51_Agent.test(env_fn, test_episodes) + xuance.torch.agent.qlearning_family.c51_agent.C51_Agent.test(env_fn, test_episodes) Test the trained model. @@ -81,7 +81,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class C51_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/ddpg.rst b/docs/source/documents/api/agents/drl/ddpg.rst index a30811bf2..3bfb1f300 100644 --- a/docs/source/documents/api/agents/drl/ddpg.rst +++ b/docs/source/documents/api/agents/drl/ddpg.rst @@ -8,12 +8,12 @@ DDPG_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.policy_gradient.ddpg_agent.DDPG_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.policy_gradient.ddpg_agent.DDPG_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizers of actor and critic that update the parameters. @@ -24,7 +24,7 @@ DDPG_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.policy_gradient.ddpg_agent.DDPG_Agent._action(obs, noise_scale) + xuance.torch.agent.policy_gradient.ddpg_agent.DDPG_Agent._action(obs, noise_scale) Calculate actions according to the observations. @@ -36,7 +36,7 @@ DDPG_Agent :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.policy_gradient.ddpg_agent.DDPG_Agent.train(train_steps) + xuance.torch.agent.policy_gradient.ddpg_agent.DDPG_Agent.train(train_steps) Train the DDPG agent. @@ -44,7 +44,7 @@ DDPG_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.policy_gradient.ddpg_agent.DDPG_Agent.test(env_fn, test_episodes) + xuance.torch.agent.policy_gradient.ddpg_agent.DDPG_Agent.test(env_fn, test_episodes) Test the trained model. @@ -79,7 +79,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class DDPG_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/ddqn.rst b/docs/source/documents/api/agents/drl/ddqn.rst index 7d8888b59..3020c54e6 100644 --- a/docs/source/documents/api/agents/drl/ddqn.rst +++ b/docs/source/documents/api/agents/drl/ddqn.rst @@ -10,12 +10,12 @@ DQN with double q-learning trick. **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.qlearning_family.ddqn_agent.DDQN_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.qlearning_family.ddqn_agent.DDQN_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -26,7 +26,7 @@ DQN with double q-learning trick. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.qlearning_family.ddqn_agent.DDQN_Agent._action(obs, egreedy) + xuance.torch.agent.qlearning_family.ddqn_agent.DDQN_Agent._action(obs, egreedy) Calculate actions according to the observations. @@ -38,7 +38,7 @@ DQN with double q-learning trick. :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.qlearning_family.ddqn_agent.DDQN_Agent.train(train_steps) + xuance.torch.agent.qlearning_family.ddqn_agent.DDQN_Agent.train(train_steps) Train the Double DQN agent. @@ -46,7 +46,7 @@ DQN with double q-learning trick. :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.qlearning_family.ddqn_agent.DDQN_Agent.test(env_fn, test_episodes) + xuance.torch.agent.qlearning_family.ddqn_agent.DDQN_Agent.test(env_fn, test_episodes) Test the trained model. @@ -82,7 +82,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class DDQN_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/dqn.rst b/docs/source/documents/api/agents/drl/dqn.rst index 5fabbb4f0..89b9d2648 100644 --- a/docs/source/documents/api/agents/drl/dqn.rst +++ b/docs/source/documents/api/agents/drl/dqn.rst @@ -8,12 +8,12 @@ DQN_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.qlearning_family.dqn_agent.DQN_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.qlearning_family.dqn_agent.DQN_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ DQN_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.qlearning_family.dqn_agent.DQN_Agent._action(obs, egreedy) + xuance.torch.agent.qlearning_family.dqn_agent.DQN_Agent._action(obs, egreedy) Calculate actions according to the observations. @@ -36,7 +36,7 @@ DQN_Agent :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.qlearning_family.dqn_agent.DQN_Agent.train(train_steps) + xuance.torch.agent.qlearning_family.dqn_agent.DQN_Agent.train(train_steps) Train the DQN agent. @@ -44,7 +44,7 @@ DQN_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.qlearning_family.dqn_agent.DQN_Agent.test(env_fn, test_episodes) + xuance.torch.agent.qlearning_family.dqn_agent.DQN_Agent.test(env_fn, test_episodes) Test the trained model. @@ -80,7 +80,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class DQN_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/dueldqn.rst b/docs/source/documents/api/agents/drl/dueldqn.rst index 4ff3ac80e..37d7c38a2 100644 --- a/docs/source/documents/api/agents/drl/dueldqn.rst +++ b/docs/source/documents/api/agents/drl/dueldqn.rst @@ -8,12 +8,12 @@ DuelDQN_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.qlearning_family.dueldqn_agent.DuelDQN_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.qlearning_family.dueldqn_agent.DuelDQN_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ DuelDQN_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.qlearning_family.dueldqn_agent.DuelDQN_Agent._action(obs, egreedy) + xuance.torch.agent.qlearning_family.dueldqn_agent.DuelDQN_Agent._action(obs, egreedy) Calculate actions according to the observations. @@ -36,7 +36,7 @@ DuelDQN_Agent :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.qlearning_family.dueldqn_agent.DuelDQN_Agent.train(train_steps) + xuance.torch.agent.qlearning_family.dueldqn_agent.DuelDQN_Agent.train(train_steps) Train the Duel-DQN agent. @@ -44,7 +44,7 @@ DuelDQN_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.qlearning_family.dueldqn_agent.DuelDQN_Agent.test(env_fn, test_episodes) + xuance.torch.agent.qlearning_family.dueldqn_agent.DuelDQN_Agent.test(env_fn, test_episodes) Test the trained model. @@ -80,7 +80,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class DuelDQN_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/mpdqn.rst b/docs/source/documents/api/agents/drl/mpdqn.rst index ef2d8f520..8197e602e 100644 --- a/docs/source/documents/api/agents/drl/mpdqn.rst +++ b/docs/source/documents/api/agents/drl/mpdqn.rst @@ -8,12 +8,12 @@ MPDQN_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.policy_gradient.mpdqn_agent.MPDQN_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.policy_gradient.mpdqn_agent.MPDQN_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ MPDQN_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.policy_gradient.mpdqn_agent.MPDQN_Agent._action(obs, egreedy) + xuance.torch.agent.policy_gradient.mpdqn_agent.MPDQN_Agent._action(obs, egreedy) Calculate actions according to the observations. @@ -36,7 +36,7 @@ MPDQN_Agent :rtype: np.ndarray, np.ndarray, np.ndarray .. py:function:: - xuanpolicy.torch.agent.policy_gradient.mpdqn_agent.MPDQN_Agent.pad_action(disaction, conaction) + xuance.torch.agent.policy_gradient.mpdqn_agent.MPDQN_Agent.pad_action(disaction, conaction) :param disaction: The discrete actions. :type disaction: numpy.ndarray @@ -46,7 +46,7 @@ MPDQN_Agent :rtype: tuple(numpy.ndarray, numpy.ndarray) .. py:function:: - xuanpolicy.torch.agent.policy_gradient.mpdqn_agent.MPDQN_Agent.train(train_steps) + xuance.torch.agent.policy_gradient.mpdqn_agent.MPDQN_Agent.train(train_steps) Train the MPDQN agent. @@ -54,7 +54,7 @@ MPDQN_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.policy_gradient.mpdqn_agent.MPDQN_Agent.test(env_fn, test_episodes) + xuance.torch.agent.policy_gradient.mpdqn_agent.MPDQN_Agent.test(env_fn, test_episodes) Test the trained model. @@ -90,7 +90,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * import gym from gym import spaces diff --git a/docs/source/documents/api/agents/drl/noisydqn.rst b/docs/source/documents/api/agents/drl/noisydqn.rst index ee9d4b0a3..884fac6fd 100644 --- a/docs/source/documents/api/agents/drl/noisydqn.rst +++ b/docs/source/documents/api/agents/drl/noisydqn.rst @@ -8,12 +8,12 @@ NoisyDQN_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.qlearning_family.noisydqn_agent.NoisyDQN_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.qlearning_family.noisydqn_agent.NoisyDQN_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ NoisyDQN_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.qlearning_family.noisydqn_agent.NoisyDQN_Agent._action(obs, egreedy) + xuance.torch.agent.qlearning_family.noisydqn_agent.NoisyDQN_Agent._action(obs, egreedy) Calculate actions according to the observations. @@ -36,7 +36,7 @@ NoisyDQN_Agent :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.qlearning_family.noisydqn_agent.NoisyDQN_Agent.train(train_steps) + xuance.torch.agent.qlearning_family.noisydqn_agent.NoisyDQN_Agent.train(train_steps) Train the Noisy-DQN agent. @@ -44,7 +44,7 @@ NoisyDQN_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.qlearning_family.noisydqn_agent.NoisyDQN_Agent.test(env_fn, test_episodes) + xuance.torch.agent.qlearning_family.noisydqn_agent.NoisyDQN_Agent.test(env_fn, test_episodes) Test the trained model. @@ -80,7 +80,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class NoisyDQN_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/pdqn.rst b/docs/source/documents/api/agents/drl/pdqn.rst index e8a2f96d2..3731a58a7 100644 --- a/docs/source/documents/api/agents/drl/pdqn.rst +++ b/docs/source/documents/api/agents/drl/pdqn.rst @@ -8,12 +8,12 @@ PDQN_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.policy_gradient.pdqn_agent.PDQN_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.policy_gradient.pdqn_agent.PDQN_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ PDQN_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.policy_gradient.pdqn_agent.PDQN_Agent._action(obs, egreedy) + xuance.torch.agent.policy_gradient.pdqn_agent.PDQN_Agent._action(obs, egreedy) Calculate actions according to the observations. @@ -36,7 +36,7 @@ PDQN_Agent :rtype: np.ndarray, np.ndarray, np.ndarray .. py:function:: - xuanpolicy.torch.agent.policy_gradient.pdqn_agent.PDQN_Agent.pad_action(disaction, conaction) + xuance.torch.agent.policy_gradient.pdqn_agent.PDQN_Agent.pad_action(disaction, conaction) :param disaction: The discrete actions. :type disaction: numpy.ndarray @@ -46,7 +46,7 @@ PDQN_Agent :rtype: tuple(numpy.ndarray, numpy.ndarray) .. py:function:: - xuanpolicy.torch.agent.policy_gradient.pdqn_agent.PDQN_Agent.train(train_steps) + xuance.torch.agent.policy_gradient.pdqn_agent.PDQN_Agent.train(train_steps) Train the PDQN agent. @@ -54,7 +54,7 @@ PDQN_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.policy_gradient.pdqn_agent.PDQN_Agent.test(env_fn, test_episodes) + xuance.torch.agent.policy_gradient.pdqn_agent.PDQN_Agent.test(env_fn, test_episodes) Test the trained model. @@ -92,7 +92,7 @@ Source Code import numpy as np - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * import gym from gym import spaces diff --git a/docs/source/documents/api/agents/drl/perdqn.rst b/docs/source/documents/api/agents/drl/perdqn.rst index 2a079615a..c790164c8 100644 --- a/docs/source/documents/api/agents/drl/perdqn.rst +++ b/docs/source/documents/api/agents/drl/perdqn.rst @@ -8,12 +8,12 @@ PerDQN_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.qlearning_family.perdqn_agent.PerDQN_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.qlearning_family.perdqn_agent.PerDQN_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ PerDQN_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.qlearning_family.perdqn_agent.PerDQN_Agent._action(obs, egreedy) + xuance.torch.agent.qlearning_family.perdqn_agent.PerDQN_Agent._action(obs, egreedy) Calculate actions according to the observations. @@ -36,7 +36,7 @@ PerDQN_Agent :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.qlearning_family.perdqn_agent.PerDQN_Agent.train(train_steps) + xuance.torch.agent.qlearning_family.perdqn_agent.PerDQN_Agent.train(train_steps) Train the PerDQN agent. @@ -44,7 +44,7 @@ PerDQN_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.qlearning_family.perdqn_agent.PerDQN_Agent.test(env_fn, test_episodes) + xuance.torch.agent.qlearning_family.perdqn_agent.PerDQN_Agent.test(env_fn, test_episodes) Test the trained model. @@ -80,7 +80,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class PerDQN_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/pg.rst b/docs/source/documents/api/agents/drl/pg.rst index b8bb9fb94..08f61ad93 100644 --- a/docs/source/documents/api/agents/drl/pg.rst +++ b/docs/source/documents/api/agents/drl/pg.rst @@ -8,12 +8,12 @@ PG_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.policy_gradient.pg_agent.PG_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.policy_gradient.pg_agent.PG_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ PG_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.policy_gradient.pg_agent.PG_Agent._action(obs) + xuance.torch.agent.policy_gradient.pg_agent.PG_Agent._action(obs) Calculate actions according to the observations. @@ -34,7 +34,7 @@ PG_Agent :rtype: np.ndarray, np.ndarray .. py:function:: - xuanpolicy.torch.agent.policy_gradient.pg_agent.PG_Agent.train(train_steps) + xuance.torch.agent.policy_gradient.pg_agent.PG_Agent.train(train_steps) Train the PG agent. @@ -42,7 +42,7 @@ PG_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.policy_gradient.pg_agent.PG_Agent.test(env_fn, test_episodes) + xuance.torch.agent.policy_gradient.pg_agent.PG_Agent.test(env_fn, test_episodes) Test the trained model. @@ -77,7 +77,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class PG_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/ppg.rst b/docs/source/documents/api/agents/drl/ppg.rst index dc083075f..2f30f5334 100644 --- a/docs/source/documents/api/agents/drl/ppg.rst +++ b/docs/source/documents/api/agents/drl/ppg.rst @@ -8,12 +8,12 @@ PPG_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.policy_gradient.ppg_agent.PPG_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.policy_gradient.ppg_agent.PPG_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ PPG_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.policy_gradient.ppg_agent.PPG_Agent._action(obs) + xuance.torch.agent.policy_gradient.ppg_agent.PPG_Agent._action(obs) Calculate actions according to the observations. @@ -34,7 +34,7 @@ PPG_Agent :rtype: np.ndarray, np.ndarray, torch.distributions .. py:function:: - xuanpolicy.torch.agent.policy_gradient.ppg_agent.PPG_Agent.train(train_steps) + xuance.torch.agent.policy_gradient.ppg_agent.PPG_Agent.train(train_steps) Train the PPG agent. @@ -42,7 +42,7 @@ PPG_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.policy_gradient.ppg_agent.PPG_Agent.test(env_fn, test_episodes) + xuance.torch.agent.policy_gradient.ppg_agent.PPG_Agent.test(env_fn, test_episodes) Test the trained model. @@ -77,7 +77,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class PPG_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/ppo_clip.rst b/docs/source/documents/api/agents/drl/ppo_clip.rst index c9a9bfd78..acfad893d 100644 --- a/docs/source/documents/api/agents/drl/ppo_clip.rst +++ b/docs/source/documents/api/agents/drl/ppo_clip.rst @@ -8,12 +8,12 @@ PPOCLIP_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.policy_gradient.ppoclip_agent.PPOCLIP_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.policy_gradient.ppoclip_agent.PPOCLIP_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ PPOCLIP_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.policy_gradient.ppoclip_agent.PPOCLIP_Agent._action(obs) + xuance.torch.agent.policy_gradient.ppoclip_agent.PPOCLIP_Agent._action(obs) Calculate actions according to the observations. @@ -34,7 +34,7 @@ PPOCLIP_Agent :rtype: np.ndarray, np.ndarray .. py:function:: - xuanpolicy.torch.agent.policy_gradient.ppoclip_agent.PPOCLIP_Agent.train(train_steps) + xuance.torch.agent.policy_gradient.ppoclip_agent.PPOCLIP_Agent.train(train_steps) Train the PPO agent. @@ -42,7 +42,7 @@ PPOCLIP_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.policy_gradient.ppoclip_agent.PPOCLIP_Agent.test(env_fn, test_episodes) + xuance.torch.agent.policy_gradient.ppoclip_agent.PPOCLIP_Agent.test(env_fn, test_episodes) Test the trained model. @@ -77,7 +77,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class PPOCLIP_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/ppo_kl.rst b/docs/source/documents/api/agents/drl/ppo_kl.rst index e42e1a6fb..5de10a65f 100644 --- a/docs/source/documents/api/agents/drl/ppo_kl.rst +++ b/docs/source/documents/api/agents/drl/ppo_kl.rst @@ -8,12 +8,12 @@ PPOKL_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.policy_gradient.ppokl_agent.PPOKL_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.policy_gradient.ppokl_agent.PPOKL_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ PPOKL_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.policy_gradient.ppokl_agent.PPOKL_Agent._action(obs) + xuance.torch.agent.policy_gradient.ppokl_agent.PPOKL_Agent._action(obs) Calculate actions according to the observations. @@ -34,7 +34,7 @@ PPOKL_Agent :rtype: np.ndarray, np.ndarray .. py:function:: - xuanpolicy.torch.agent.policy_gradient.ppokl_agent.PPOKL_Agent.train(train_steps) + xuance.torch.agent.policy_gradient.ppokl_agent.PPOKL_Agent.train(train_steps) Train the PPO agent. @@ -42,7 +42,7 @@ PPOKL_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.policy_gradient.ppokl_agent.PPOKL_Agent.test(env_fn, test_episodes) + xuance.torch.agent.policy_gradient.ppokl_agent.PPOKL_Agent.test(env_fn, test_episodes) Test the trained model. @@ -77,7 +77,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class PPOKL_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/qrdqn.rst b/docs/source/documents/api/agents/drl/qrdqn.rst index 435e756e5..453ee9f44 100644 --- a/docs/source/documents/api/agents/drl/qrdqn.rst +++ b/docs/source/documents/api/agents/drl/qrdqn.rst @@ -8,12 +8,12 @@ QRDQN_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.qlearning_family.qrdqn_agent.QRDQN_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.qlearning_family.qrdqn_agent.QRDQN_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ QRDQN_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.qlearning_family.qrdqn_agent.QRDQN_Agent._action(obs, egreedy) + xuance.torch.agent.qlearning_family.qrdqn_agent.QRDQN_Agent._action(obs, egreedy) Calculate actions according to the observations. @@ -36,7 +36,7 @@ QRDQN_Agent :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.qlearning_family.qrdqn_agent.QRDQN_Agent.train(train_steps) + xuance.torch.agent.qlearning_family.qrdqn_agent.QRDQN_Agent.train(train_steps) Train the QRDQN agent. @@ -44,7 +44,7 @@ QRDQN_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.qlearning_family.qrdqn_agent.QRDQN_Agent.test(env_fn, test_episodes) + xuance.torch.agent.qlearning_family.qrdqn_agent.QRDQN_Agent.test(env_fn, test_episodes) Test the trained model. @@ -80,7 +80,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class QRDQN_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/sac.rst b/docs/source/documents/api/agents/drl/sac.rst index 5852eee47..f3be20a87 100644 --- a/docs/source/documents/api/agents/drl/sac.rst +++ b/docs/source/documents/api/agents/drl/sac.rst @@ -8,12 +8,12 @@ SAC_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.policy_gradient.sac_agent.SAC_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.policy_gradient.sac_agent.SAC_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizers of actor and critic that update the parameters. @@ -24,7 +24,7 @@ SAC_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.policy_gradient.sac_agent.SAC_Agent._action(obs) + xuance.torch.agent.policy_gradient.sac_agent.SAC_Agent._action(obs) Calculate actions according to the observations. @@ -34,7 +34,7 @@ SAC_Agent :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.policy_gradient.sac_agent.SAC_Agent.train(train_steps) + xuance.torch.agent.policy_gradient.sac_agent.SAC_Agent.train(train_steps) Train the SAC agent. @@ -42,7 +42,7 @@ SAC_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.policy_gradient.sac_agent.SAC_Agent.test(env_fn, test_episodes) + xuance.torch.agent.policy_gradient.sac_agent.SAC_Agent.test(env_fn, test_episodes) Test the trained model. @@ -77,7 +77,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class SAC_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/sac_dis.rst b/docs/source/documents/api/agents/drl/sac_dis.rst index 998543749..8fd487471 100644 --- a/docs/source/documents/api/agents/drl/sac_dis.rst +++ b/docs/source/documents/api/agents/drl/sac_dis.rst @@ -8,12 +8,12 @@ SACDIS_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.policy_gradient.sacdis_agent.SACDIS_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.policy_gradient.sacdis_agent.SACDIS_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizers of actor and critic that update the parameters. @@ -24,7 +24,7 @@ SACDIS_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.policy_gradient.sacdis_agent.SACDIS_Agent._action(obs) + xuance.torch.agent.policy_gradient.sacdis_agent.SACDIS_Agent._action(obs) Calculate actions according to the observations. @@ -34,7 +34,7 @@ SACDIS_Agent :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.policy_gradient.sacdis_agent.SACDIS_Agent.train(train_steps) + xuance.torch.agent.policy_gradient.sacdis_agent.SACDIS_Agent.train(train_steps) Train the SACDIS agent. @@ -42,7 +42,7 @@ SACDIS_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.policy_gradient.sacdis_agent.SACDIS_Agent.test(env_fn, test_episodes) + xuance.torch.agent.policy_gradient.sacdis_agent.SACDIS_Agent.test(env_fn, test_episodes) Test the trained model. @@ -77,7 +77,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class SACDIS_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/drl/spdqn.rst b/docs/source/documents/api/agents/drl/spdqn.rst index d5edb3279..47056dc42 100644 --- a/docs/source/documents/api/agents/drl/spdqn.rst +++ b/docs/source/documents/api/agents/drl/spdqn.rst @@ -8,12 +8,12 @@ SPDQN_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.policy_gradient.spdqn_agent.SPDQN_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.policy_gradient.spdqn_agent.SPDQN_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizer that updates the parameters. @@ -24,7 +24,7 @@ SPDQN_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.policy_gradient.spdqn_agent.SPDQN_Agent._action(obs, egreedy) + xuance.torch.agent.policy_gradient.spdqn_agent.SPDQN_Agent._action(obs, egreedy) Calculate actions according to the observations. @@ -36,7 +36,7 @@ SPDQN_Agent :rtype: np.ndarray, np.ndarray, np.ndarray .. py:function:: - xuanpolicy.torch.agent.policy_gradient.spdqn_agent.SPDQN_Agent.pad_action(disaction, conaction) + xuance.torch.agent.policy_gradient.spdqn_agent.SPDQN_Agent.pad_action(disaction, conaction) :param disaction: The discrete actions. :type disaction: numpy.ndarray @@ -46,7 +46,7 @@ SPDQN_Agent :rtype: tuple(numpy.ndarray, numpy.ndarray) .. py:function:: - xuanpolicy.torch.agent.policy_gradient.spdqn_agent.SPDQN_Agent.train(train_steps) + xuance.torch.agent.policy_gradient.spdqn_agent.SPDQN_Agent.train(train_steps) Train the SPDQN agent. @@ -54,7 +54,7 @@ SPDQN_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.policy_gradient.spdqn_agent.SPDQN_Agent.test(env_fn, test_episodes) + xuance.torch.agent.policy_gradient.spdqn_agent.SPDQN_Agent.test(env_fn, test_episodes) Test the trained model. @@ -90,7 +90,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * import gym from gym import spaces diff --git a/docs/source/documents/api/agents/drl/td3.rst b/docs/source/documents/api/agents/drl/td3.rst index dc26c8b92..a695e1d57 100644 --- a/docs/source/documents/api/agents/drl/td3.rst +++ b/docs/source/documents/api/agents/drl/td3.rst @@ -8,12 +8,12 @@ TD3_Agent **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.policy_gradient.td3_agent.TD3_Agent(config, envs, policy, optimizer, scheduler, device) + xuance.torch.agent.policy_gradient.td3_agent.TD3_Agent(config, envs, policy, optimizer, scheduler, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param optimizer: The optimizers of actor and critic that update the parameters. @@ -24,7 +24,7 @@ TD3_Agent :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.policy_gradient.td3_agent.TD3_Agent._action(obs, noise_scale) + xuance.torch.agent.policy_gradient.td3_agent.TD3_Agent._action(obs, noise_scale) Calculate actions according to the observations. @@ -36,7 +36,7 @@ TD3_Agent :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.policy_gradient.td3_agent.TD3_Agent.train(train_steps) + xuance.torch.agent.policy_gradient.td3_agent.TD3_Agent.train(train_steps) Train the TD3 agent. @@ -44,7 +44,7 @@ TD3_Agent :type train_steps: int .. py:function:: - xuanpolicy.torch.agent.policy_gradient.td3_agent.TD3_Agent.test(env_fn, test_episodes) + xuance.torch.agent.policy_gradient.td3_agent.TD3_Agent.test(env_fn, test_episodes) Test the trained model. @@ -79,7 +79,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class TD3_Agent(Agent): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/basic_marl_class.rst b/docs/source/documents/api/agents/marl/basic_marl_class.rst index 42d168875..41a298c61 100644 --- a/docs/source/documents/api/agents/marl/basic_marl_class.rst +++ b/docs/source/documents/api/agents/marl/basic_marl_class.rst @@ -1,23 +1,23 @@ MARLAgent ======================= -To create new MARL agents, you should build a class inherit from ``xuanpolicy.torch.agents.agents_marl.MARLAgent`` , ``xuanpolicy.tensorflow.agents.agents_marl.MARLAgent``, or ``xuanpolicy.mindspore.agents.agents_marl.MARLAgent``. +To create new MARL agents, you should build a class inherit from ``xuance.torch.agents.agents_marl.MARLAgent`` , ``xuance.tensorflow.agents.agents_marl.MARLAgent``, or ``xuance.mindspore.agents.agents_marl.MARLAgent``. **PyTorch:** .. py:class:: - xuanpolicy.torch.agents.agents_marl.MARLAgent(config, envs, policy, memory, learner, device, log_dir, model_dir) + xuance.torch.agents.agents_marl.MARLAgent(config, envs, policy, memory, learner, device, log_dir, model_dir) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param memory: Experice replay buffer. - :type memory: xuanpolicy.common.memory_tools.Buffer + :type memory: xuance.common.memory_tools.Buffer :param learner: The learner that updates parameters of policy. - :type learner: xuanpolicy.torch.learner.LearnerMAS + :type learner: xuance.torch.learner.LearnerMAS :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device :param log_dir: The directory of log file, default is "./logs/". @@ -25,14 +25,14 @@ To create new MARL agents, you should build a class inherit from ``xuanpolicy.to :param model_dir: The directory of model file, default is "./models/". :type model_dir: str -.. py:function:: xuanpolicy.torch.agents.agents_marl.MARLAgent.save_model(model_name) +.. py:function:: xuance.torch.agents.agents_marl.MARLAgent.save_model(model_name) Save the model. :param model_name: The model's name to be saved. :type model_name: str -.. py:function:: xuanpolicy.torch.agents.agents_marl.MARLAgent.load_model(path, seed) +.. py:function:: xuance.torch.agents.agents_marl.MARLAgent.load_model(path, seed) Load a model by specifying the ``path`` and ``seed`` . @@ -41,14 +41,14 @@ To create new MARL agents, you should build a class inherit from ``xuanpolicy.to :param seed: Select the seed that model was trained with if it exits. :type seed: int -.. py:function:: xuanpolicy.torch.agents.agents_marl.MARLAgent.act(**kwargs) +.. py:function:: xuance.torch.agents.agents_marl.MARLAgent.act(**kwargs) Get actions for executing according to the joint observations, global states, available actions, etc. :param kwargs: Inputs informations. :type observations: Dict -.. py:function:: xuanpolicy.torch.agents.agents_marl.MARLAgent.train(**kwargs) +.. py:function:: xuance.torch.agents.agents_marl.MARLAgent.train(**kwargs) Train the multi-agent reinforcement learning models. @@ -59,7 +59,7 @@ To create new MARL agents, you should build a class inherit from ``xuanpolicy.to .. py:class:: - xuanpolicy.torch.agents.agents_marl.linear_decay_or_increase(start, end, step_length) + xuance.torch.agents.agents_marl.linear_decay_or_increase(start, end, step_length) :param start: Start factor. :type start: np.float @@ -68,23 +68,23 @@ To create new MARL agents, you should build a class inherit from ``xuanpolicy.to :param step_length: The number of steps the factor decays or increases. :type step_length: int -.. py:function:: xuanpolicy.torch.agents.agents_marl.linear_decay_or_increase.update() +.. py:function:: xuance.torch.agents.agents_marl.linear_decay_or_increase.update() Update the factor once. .. py:class:: - xuanpolicy.torch.agents.agents_marl.RandomAgents(args, envs, device=None) + xuance.torch.agents.agents_marl.RandomAgents(args, envs, device=None) :param args: Provides hyper parameters. :type args: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agents.agents_marl.RandomAgents.act() + xuance.torch.agents.agents_marl.RandomAgents.act() Provide random actions for RandomAgents. @@ -99,18 +99,18 @@ To create new MARL agents, you should build a class inherit from ``xuanpolicy.to **TensorFlow:** .. py:class:: - xuanpolicy.tensorflow.agents.agents_marl.MARLAgent(config, envs, policy, memory, learner, device, log_dir, model_dir) + xuance.tensorflow.agents.agents_marl.MARLAgent(config, envs, policy, memory, learner, device, log_dir, model_dir) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param memory: Experice replay buffer. - :type memory: xuanpolicy.common.memory_tools.Buffer + :type memory: xuance.common.memory_tools.Buffer :param learner: The learner that updates parameters of policy. - :type learner: xuanpolicy.tensorflow.learner.Learner + :type learner: xuance.tensorflow.learner.Learner :param device: Choose CPU or GPU to train the model. :type device: str :param log_dir: The directory of log file, default is "./logs/". @@ -126,16 +126,16 @@ To create new MARL agents, you should build a class inherit from ``xuanpolicy.to **MindSpore:** .. py:class:: - xuanpolicy.mindspore.agents.agents_marl.MARLAgent(envs, policy, memory, learner, device, log_dir, model_dir) + xuance.mindspore.agents.agents_marl.MARLAgent(envs, policy, memory, learner, device, log_dir, model_dir) :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param policy: The policy that provides actions and values. :type policy: nn.Module :param memory: Experice replay buffer. - :type memory: xuanpolicy.common.memory_tools.Buffer + :type memory: xuance.common.memory_tools.Buffer :param learner: The learner that updates parameters of policy. - :type learner: xuanpolicy.mindspore.learner.Learner + :type learner: xuance.mindspore.learner.Learner :param device: Choose CPU or GPU to train the model. :type device: str :param log_dir: The directory of log file, default is "./logs/". @@ -158,7 +158,7 @@ Source Code .. code-block:: python import os.path - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class MARLAgents(object): @@ -247,7 +247,7 @@ Source Code .. code-block:: python - from xuanpolicy.tensorflow.agents import * + from xuance.tensorflow.agents import * class MARLAgents(object): def __init__(self, @@ -355,7 +355,7 @@ Source Code import mindspore as ms import mindspore.ops as ops from mindspore import Tensor - from xuanpolicy.mindspore.agents import * + from xuance.mindspore.agents import * class MARLAgents(object): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/coma.rst b/docs/source/documents/api/agents/marl/coma.rst index abd50ed63..0d85ac500 100644 --- a/docs/source/documents/api/agents/marl/coma.rst +++ b/docs/source/documents/api/agents/marl/coma.rst @@ -8,17 +8,17 @@ COMA_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.coma_agents.COMA_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.coma_agents.COMA_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.coma_agents.COMA_Agents.act(obs_n, *rnn_hidden, avail_actions=None, state=None, test_mode=False) + xuance.torch.agent.mutli_agent_rl.coma_agents.COMA_Agents.act(obs_n, *rnn_hidden, avail_actions=None, state=None, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -36,7 +36,7 @@ COMA_Agents :rtype: tuple(numpy.ndarray, numpy.ndarray), np.ndarray, np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.coma_agents.COMA_Agents.train(i_step) + xuance.torch.agent.mutli_agent_rl.coma_agents.COMA_Agents.train(i_step) Train the multi-agent reinforcement learning model. @@ -72,8 +72,8 @@ Source Code .. code-block:: python import torch - from xuanpolicy.torch.agents import * - from xuanpolicy.torch.agents.agents_marl import linear_decay_or_increase + from xuance.torch.agents import * + from xuance.torch.agents.agents_marl import linear_decay_or_increase class COMA_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/dcg.rst b/docs/source/documents/api/agents/marl/dcg.rst index 3be9bf172..0d92d064c 100644 --- a/docs/source/documents/api/agents/marl/dcg.rst +++ b/docs/source/documents/api/agents/marl/dcg.rst @@ -8,17 +8,17 @@ DCG_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.dcg_agents.DCG_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.dcg_agents.DCG_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.dcg_agents.DCG_Agents.act(obs_n, *rnn_hidden, avail_actions=None, test_mode=False) + xuance.torch.agent.mutli_agent_rl.dcg_agents.DCG_Agents.act(obs_n, *rnn_hidden, avail_actions=None, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -34,7 +34,7 @@ DCG_Agents :rtype: tuple(numpy.ndarray, numpy.ndarray), np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.dcg_agents.DCG_Agents.train(i_step) + xuance.torch.agent.mutli_agent_rl.dcg_agents.DCG_Agents.train(i_step) Train the multi-agent reinforcement learning model. @@ -70,7 +70,7 @@ Source Code .. code-block:: python import torch.nn - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class DCG_Agents(MARLAgents): def __init__(self, @@ -92,7 +92,7 @@ Source Code else: representation = REGISTRY_Representation[config.representation](*input_representation) repre_state_dim = representation.output_shapes['state'][0] - from xuanpolicy.torch.policies.coordination_graph import DCG_utility, DCG_payoff, Coordination_Graph + from xuance.torch.policies.coordination_graph import DCG_utility, DCG_payoff, Coordination_Graph utility = DCG_utility(repre_state_dim, config.hidden_utility_dim, config.dim_act).to(device) payoffs = DCG_payoff(repre_state_dim * 2, config.hidden_payoff_dim, config.dim_act, config).to(device) dcgraph = Coordination_Graph(config.n_agents, config.graph_type) @@ -133,7 +133,7 @@ Source Code config.done_shape, envs.num_envs, config.buffer_size, config.batch_size) memory = buffer(*input_buffer, max_episode_length=envs.max_episode_length, dim_act=config.dim_act) - from xuanpolicy.torch.learners.multi_agent_rl.dcg_learner import DCG_Learner + from xuance.torch.learners.multi_agent_rl.dcg_learner import DCG_Learner learner = DCG_Learner(config, policy, optimizer, scheduler, config.device, config.model_dir, config.gamma, config.sync_frequency) diff --git a/docs/source/documents/api/agents/marl/iddpg.rst b/docs/source/documents/api/agents/marl/iddpg.rst index 3c41d821c..46b1b19fd 100644 --- a/docs/source/documents/api/agents/marl/iddpg.rst +++ b/docs/source/documents/api/agents/marl/iddpg.rst @@ -8,17 +8,17 @@ IDDPG_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.iddpg_agents.IDDPG_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.iddpg_agents.IDDPG_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.iddpg_agents.IDDPG_Agents.act(obs_n, test_mode=False) + xuance.torch.agent.mutli_agent_rl.iddpg_agents.IDDPG_Agents.act(obs_n, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -30,7 +30,7 @@ IDDPG_Agents :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.iddpg_agents.IDDPG_Agents.train(i_episode) + xuance.torch.agent.mutli_agent_rl.iddpg_agents.IDDPG_Agents.train(i_episode) Train the multi-agent reinforcement learning model. @@ -65,7 +65,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class IDDPG_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/ippo.rst b/docs/source/documents/api/agents/marl/ippo.rst index e3925988c..b363f077a 100644 --- a/docs/source/documents/api/agents/marl/ippo.rst +++ b/docs/source/documents/api/agents/marl/ippo.rst @@ -8,12 +8,12 @@ IPPO_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.ippo_agents.IPPO_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.ippo_agents.IPPO_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device diff --git a/docs/source/documents/api/agents/marl/iql.rst b/docs/source/documents/api/agents/marl/iql.rst index 1421187dd..d09dbf1f8 100644 --- a/docs/source/documents/api/agents/marl/iql.rst +++ b/docs/source/documents/api/agents/marl/iql.rst @@ -8,17 +8,17 @@ IQL_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.iql_agents.IQL_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.iql_agents.IQL_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.iql_agents.IQL_Agents.act(obs_n, *rnn_hidden, avail_actions=None, test_mode=False) + xuance.torch.agent.mutli_agent_rl.iql_agents.IQL_Agents.act(obs_n, *rnn_hidden, avail_actions=None, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -34,7 +34,7 @@ IQL_Agents :rtype: tuple(numpy.ndarray, numpy.ndarray), np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.iql_agents.IQL_Agents.train(i_step) + xuance.torch.agent.mutli_agent_rl.iql_agents.IQL_Agents.train(i_step) Train the multi-agent reinforcement learning model. @@ -69,7 +69,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class IQL_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/isac.rst b/docs/source/documents/api/agents/marl/isac.rst index cda1ab151..d0ad06cc5 100644 --- a/docs/source/documents/api/agents/marl/isac.rst +++ b/docs/source/documents/api/agents/marl/isac.rst @@ -8,17 +8,17 @@ ISAC_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.isac_agents.ISAC_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.isac_agents.ISAC_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.isac_agents.ISAC_Agents.act(obs_n, test_mode=False) + xuance.torch.agent.mutli_agent_rl.isac_agents.ISAC_Agents.act(obs_n, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -30,7 +30,7 @@ ISAC_Agents :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.isac_agents.ISAC_Agents.train(i_episode) + xuance.torch.agent.mutli_agent_rl.isac_agents.ISAC_Agents.train(i_episode) Train the multi-agent reinforcement learning model. @@ -65,7 +65,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class ISAC_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/maddpg.rst b/docs/source/documents/api/agents/marl/maddpg.rst index 542ec46a9..a02c6603a 100644 --- a/docs/source/documents/api/agents/marl/maddpg.rst +++ b/docs/source/documents/api/agents/marl/maddpg.rst @@ -8,17 +8,17 @@ MADDPG_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.maddpg_agents.MADDPG_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.maddpg_agents.MADDPG_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.maddpg_agents.MADDPG_Agents.act(obs_n, test_mode=False) + xuance.torch.agent.mutli_agent_rl.maddpg_agents.MADDPG_Agents.act(obs_n, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -30,7 +30,7 @@ MADDPG_Agents :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.maddpg_agents.MADDPG_Agents.train(i_episode) + xuance.torch.agent.mutli_agent_rl.maddpg_agents.MADDPG_Agents.train(i_episode) Train the multi-agent reinforcement learning model. @@ -65,7 +65,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class MADDPG_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/mappo.rst b/docs/source/documents/api/agents/marl/mappo.rst index 50b7e8d0e..74ba1be34 100644 --- a/docs/source/documents/api/agents/marl/mappo.rst +++ b/docs/source/documents/api/agents/marl/mappo.rst @@ -8,17 +8,17 @@ MAPPO_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.mappo_agents.MAPPO_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.mappo_agents.MAPPO_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.mappo_agents.MAPPO_Agents.act(obs_n, *rnn_hidden, avail_actions=None, state=None, test_mode=False) + xuance.torch.agent.mutli_agent_rl.mappo_agents.MAPPO_Agents.act(obs_n, *rnn_hidden, avail_actions=None, state=None, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -36,7 +36,7 @@ MAPPO_Agents :rtype: tuple(numpy.ndarray, numpy.ndarray), np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.mappo_agents.MAPPO_Agents.train(i_step) + xuance.torch.agent.mutli_agent_rl.mappo_agents.MAPPO_Agents.train(i_step) Train the multi-agent reinforcement learning model. @@ -72,7 +72,7 @@ Source Code .. code-block:: python import torch - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class MAPPO_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/masac.rst b/docs/source/documents/api/agents/marl/masac.rst index 71c52fdcd..5bf66d292 100644 --- a/docs/source/documents/api/agents/marl/masac.rst +++ b/docs/source/documents/api/agents/marl/masac.rst @@ -8,17 +8,17 @@ MASAC_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.masac_agents.MASAC_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.masac_agents.MASAC_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.masac_agents.MASAC_Agents.act(obs_n, test_mode=False) + xuance.torch.agent.mutli_agent_rl.masac_agents.MASAC_Agents.act(obs_n, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -30,7 +30,7 @@ MASAC_Agents :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.masac_agents.MASAC_Agents.train(i_episode) + xuance.torch.agent.mutli_agent_rl.masac_agents.MASAC_Agents.train(i_episode) Train the multi-agent reinforcement learning model. @@ -65,7 +65,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class MASAC_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/matd3.rst b/docs/source/documents/api/agents/marl/matd3.rst index 55cf30594..249ba12c1 100644 --- a/docs/source/documents/api/agents/marl/matd3.rst +++ b/docs/source/documents/api/agents/marl/matd3.rst @@ -8,17 +8,17 @@ MATD3_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.matd3_agents.MATD3_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.matd3_agents.MATD3_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.matd3_agents.MATD3_Agents.act(obs_n, test_mode=False) + xuance.torch.agent.mutli_agent_rl.matd3_agents.MATD3_Agents.act(obs_n, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -30,7 +30,7 @@ MATD3_Agents :rtype: np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.matd3_agents.MATD3_Agents.train(i_episode) + xuance.torch.agent.mutli_agent_rl.matd3_agents.MATD3_Agents.train(i_episode) Train the multi-agent reinforcement learning model. @@ -65,7 +65,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class MATD3_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/mfq.rst b/docs/source/documents/api/agents/marl/mfq.rst index 96d2f725e..c549cb410 100644 --- a/docs/source/documents/api/agents/marl/mfq.rst +++ b/docs/source/documents/api/agents/marl/mfq.rst @@ -8,17 +8,17 @@ MFQ_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.mfq_agents.MFQ_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.mfq_agents.MFQ_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.mfq_agents.MFQ_Agents.act(obs_n, *rnn_hidden, act_mean=None, agent_mask=False, test_mode=False) + xuance.torch.agent.mutli_agent_rl.mfq_agents.MFQ_Agents.act(obs_n, *rnn_hidden, act_mean=None, agent_mask=False, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -36,7 +36,7 @@ MFQ_Agents :rtype: tuple(numpy.ndarray, numpy.ndarray), np.ndarray, np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.mfq_agents.MFQ_Agents.train(i_step) + xuance.torch.agent.mutli_agent_rl.mfq_agents.MFQ_Agents.train(i_step) Train the multi-agent reinforcement learning model. @@ -71,8 +71,8 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * - from xuanpolicy.torch.agents.agents_marl import linear_decay_or_increase + from xuance.torch.agents import * + from xuance.torch.agents.agents_marl import linear_decay_or_increase class MFQ_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/qmix.rst b/docs/source/documents/api/agents/marl/qmix.rst index 08e6c2756..8e7b2bdde 100644 --- a/docs/source/documents/api/agents/marl/qmix.rst +++ b/docs/source/documents/api/agents/marl/qmix.rst @@ -8,17 +8,17 @@ QMIX_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.qmix_agents.QMIX_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.qmix_agents.QMIX_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.qmix_agents.QMIX_Agents.act(obs_n, *rnn_hidden, avail_actions=None, test_mode=False) + xuance.torch.agent.mutli_agent_rl.qmix_agents.QMIX_Agents.act(obs_n, *rnn_hidden, avail_actions=None, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -34,7 +34,7 @@ QMIX_Agents :rtype: tuple(numpy.ndarray, numpy.ndarray), np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.qmix_agents.QMIX_Agents.train(i_step) + xuance.torch.agent.mutli_agent_rl.qmix_agents.QMIX_Agents.train(i_step) Train the multi-agent reinforcement learning model. @@ -69,7 +69,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class QMIX_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/qtran.rst b/docs/source/documents/api/agents/marl/qtran.rst index 16360f0fd..a2dff0798 100644 --- a/docs/source/documents/api/agents/marl/qtran.rst +++ b/docs/source/documents/api/agents/marl/qtran.rst @@ -8,17 +8,17 @@ QTRAN_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.qtran_agents.QTRAN_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.qtran_agents.QTRAN_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.qtran_agents.QTRAN_Agents.train(i_step) + xuance.torch.agent.mutli_agent_rl.qtran_agents.QTRAN_Agents.train(i_step) Train the multi-agent reinforcement learning model. @@ -53,8 +53,8 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * - from xuanpolicy.torch.agents.agents_marl import linear_decay_or_increase + from xuance.torch.agents import * + from xuance.torch.agents.agents_marl import linear_decay_or_increase class QTRAN_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/vdn.rst b/docs/source/documents/api/agents/marl/vdn.rst index 0d28dcf1e..6764932a7 100644 --- a/docs/source/documents/api/agents/marl/vdn.rst +++ b/docs/source/documents/api/agents/marl/vdn.rst @@ -8,17 +8,17 @@ VDN_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.vdn_agents.VDN_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.vdn_agents.VDN_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.vdn_agents.VDN_Agents.act(obs_n, *rnn_hidden, avail_actions=None, test_mode=False) + xuance.torch.agent.mutli_agent_rl.vdn_agents.VDN_Agents.act(obs_n, *rnn_hidden, avail_actions=None, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -34,7 +34,7 @@ VDN_Agents :rtype: tuple(numpy.ndarray, numpy.ndarray), np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.vdn_agents.VDN_Agents.train(i_step) + xuance.torch.agent.mutli_agent_rl.vdn_agents.VDN_Agents.train(i_step) Train the multi-agent reinforcement learning model. @@ -69,7 +69,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class VDN_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/agents/marl/wqmix.rst b/docs/source/documents/api/agents/marl/wqmix.rst index e432b960a..a28eb5f11 100644 --- a/docs/source/documents/api/agents/marl/wqmix.rst +++ b/docs/source/documents/api/agents/marl/wqmix.rst @@ -8,17 +8,17 @@ WQMIX_Agents **PyTorch:** .. py:class:: - xuanpolicy.torch.agent.mutli_agent_rl.wqmix_agents.WQMIX_Agents(config, envs, device) + xuance.torch.agent.mutli_agent_rl.wqmix_agents.WQMIX_Agents(config, envs, device) :param config: Provides hyper parameters. :type config: Namespace :param envs: The vectorized environments. - :type envs: xuanpolicy.environments.vector_envs.vector_env.VecEnv + :type envs: xuance.environments.vector_envs.vector_env.VecEnv :param device: Choose CPU or GPU to train the model. :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.wqmix_agents.WQMIX_Agents.act(obs_n, *rnn_hidden, avail_actions=None, test_mode=False) + xuance.torch.agent.mutli_agent_rl.wqmix_agents.WQMIX_Agents.act(obs_n, *rnn_hidden, avail_actions=None, test_mode=False) Calculate joint actions for N agents according to the joint observations. @@ -34,7 +34,7 @@ WQMIX_Agents :rtype: tuple(numpy.ndarray, numpy.ndarray), np.ndarray .. py:function:: - xuanpolicy.torch.agent.mutli_agent_rl.wqmix_agents.WQMIX_Agents.train(i_step) + xuance.torch.agent.mutli_agent_rl.wqmix_agents.WQMIX_Agents.train(i_step) Train the multi-agent reinforcement learning model. @@ -69,7 +69,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.agents import * + from xuance.torch.agents import * class WQMIX_Agents(MARLAgents): def __init__(self, diff --git a/docs/source/documents/api/configs.rst b/docs/source/documents/api/configs.rst index 2e36005d9..8fb9e06f6 100644 --- a/docs/source/documents/api/configs.rst +++ b/docs/source/documents/api/configs.rst @@ -9,13 +9,13 @@ Configs 基础参数配置 -------------------------- -基础参数配置存于xuanpolicy/config/basic.yaml文件中，示例如下： +基础参数配置存于xuance/config/basic.yaml文件中，示例如下： .. code-block:: yaml dl_toolbox: "torch" # Values: "torch", "mindspore", "tensorlayer" - project_name: "XuanPolicy_Benchmark" + project_name: "XuanCe_Benchmark" logger: "tensorboard" # Values: tensorboard, wandb. wandb_user_name: "papers_liu" @@ -42,7 +42,7 @@ Configs 算法参数配置 -------------------------- -以DQN算法在Atari环境中的参数配置为例，除了基础参数配置外，其算法参数配置存放于 xuanpolicy/configs/dqn/atari.yaml +以DQN算法在Atari环境中的参数配置为例，除了基础参数配置外，其算法参数配置存放于 xuance/configs/dqn/atari.yaml 文件中，内容如下： .. raw:: html @@ -107,8 +107,8 @@ Configs 针对场景差异较大的环境，如 ``Box2D`` 环境中的 ``CarRacing-v2`` 和 ``LunarLander`` 场景， 前者的状态输入是96*96*3的RGB图像，后者则是一个8维向量。因此，针对这两个场景的DQN算法参数配置分别存于以下两个文件中： - * xuanpolicy/configs/dqn/box2d/CarRacing-v2.yaml - * xuanpolicy/configs/dqn/box2d/LunarLander-v2.yaml + * xuance/configs/dqn/box2d/CarRacing-v2.yaml + * xuance/configs/dqn/box2d/LunarLander-v2.yaml .. raw:: html @@ -121,7 +121,7 @@ Configs .. code-block:: python - import xuanpolicy as xp + import xuance as xp runner = xp.get_runner(method='dqn', env='classic_control', env_id='CartPole-v1', diff --git a/docs/source/documents/api/learners/learner.rst b/docs/source/documents/api/learners/learner.rst index c21b03bc4..305d4b877 100644 --- a/docs/source/documents/api/learners/learner.rst +++ b/docs/source/documents/api/learners/learner.rst @@ -1,12 +1,12 @@ Learner ======================= -To create new learner, you should build a class inherit from ``xuanpolicy.torch.learners.learner.Learner`` , ``xuanpolicy.tensorflow.learners.learner.Learner``, or ``xuanpolicy.mindspore.learners.learner.Learner``. +To create new learner, you should build a class inherit from ``xuance.torch.learners.learner.Learner`` , ``xuance.tensorflow.learners.learner.Learner``, or ``xuance.mindspore.learners.learner.Learner``. **PyTorch:** .. py:class:: - xuanpolicy.torch.learners.learner.Learner(policy, optimizer, scheduler=None, device=None, model_dir="./") + xuance.torch.learners.learner.Learner(policy, optimizer, scheduler=None, device=None, model_dir="./") The basic class of the learner. @@ -21,14 +21,14 @@ To create new learner, you should build a class inherit from ``xuanpolicy.torch. :param model_dir: The directory of model file, default is "./". :type model_dir: str -.. py:function:: xuanpolicy.torch.learners.learner.Learner.save_model(model_path) +.. py:function:: xuance.torch.learners.learner.Learner.save_model(model_path) Save the model. :param model_path: The model's path. :type model_path: str -.. py:function:: xuanpolicy.torch.learners.learner.Learner.load_model(path, seed=1) +.. py:function:: xuance.torch.learners.learner.Learner.load_model(path, seed=1) Load a model by specifying the ``path`` and ``seed`` . @@ -37,7 +37,7 @@ To create new learner, you should build a class inherit from ``xuanpolicy.torch. :param seed: Select the seed that model was trained with if it exits. :type seed: int -.. py:function:: xuanpolicy.torch.learners.learner.Learner.update(*args) +.. py:function:: xuance.torch.learners.learner.Learner.update(*args) Update the policies with self.optimizer. diff --git a/docs/source/documents/api/representations/cnn.rst b/docs/source/documents/api/representations/cnn.rst index b75977345..cb51a35de 100644 --- a/docs/source/documents/api/representations/cnn.rst +++ b/docs/source/documents/api/representations/cnn.rst @@ -3,7 +3,7 @@ CNN-based Convolutional Neural Networks (CNNs) are mainly used for processing image input data to extract feature vectors. They usually take multi-channel image matrices as input and output multi-dimensional vectors. -The CNN block is defined in `./xuanpolicy/torch/utils/layers.py`, `./xuanpolicy/tensorflow/utils/layers.py` and `./xuanpolicy/mindspore/utils/layers.py`. +The CNN block is defined in `./xuance/torch/utils/layers.py`, `./xuance/tensorflow/utils/layers.py` and `./xuance/mindspore/utils/layers.py`. To instantiate this class, you need to specify the input size (`input_shape`), the filtering method (`filter`), the kernel size (`kernel_size`), the stride (`stride`), the normalization method (`normalize`), the activation function (`activation`), and the initialization method (`initialize`). @@ -17,7 +17,7 @@ When implementing this class in PyTorch, you also need to specify the device typ **PyTorch:** .. py:class:: - xuanpolicy.torch.representations.cnn.Basic_CNN(input_shape, kernels, strides, filters, normalize=None, initialize=None, activation=None, device=None) + xuance.torch.representations.cnn.Basic_CNN(input_shape, kernels, strides, filters, normalize=None, initialize=None, activation=None, device=None) :param input_shape: The shape of the inputs. :type input_shape: Sequence of int @@ -36,7 +36,7 @@ When implementing this class in PyTorch, you also need to specify the device typ :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.representations.cnn.Basic_CNN._create_network() + xuance.torch.representations.cnn.Basic_CNN._create_network() Create the convolutional neural netowrks. @@ -44,7 +44,7 @@ When implementing this class in PyTorch, you also need to specify the device typ :rtype: nn.Module .. py:function:: - xuanpolicy.torch.representations.cnn.Basic_CNN.forward(observations) + xuance.torch.representations.cnn.Basic_CNN.forward(observations) Calculate feature representation of the input observations. @@ -54,7 +54,7 @@ When implementing this class in PyTorch, you also need to specify the device typ :rtype: dict .. py:class:: - xuanpolicy.torch.representations.cnn.AC_CNN_Atari(input_shape, kernels, strides, filters, normalize=None, initialize=None, activation=None, device=None) + xuance.torch.representations.cnn.AC_CNN_Atari(input_shape, kernels, strides, filters, normalize=None, initialize=None, activation=None, device=None) :param input_shape: The shape of the inputs. :type input_shape: Sequence of int @@ -75,7 +75,7 @@ When implementing this class in PyTorch, you also need to specify the device typ :type device: Sequence of int .. py:function:: - xuanpolicy.torch.representations.cnn.AC_CNN_Atari._init_layer(layer, gain=numpy.sqrt(2), bias=0.0) + xuance.torch.representations.cnn.AC_CNN_Atari._init_layer(layer, gain=numpy.sqrt(2), bias=0.0) Initialize the weights and biases of the model. @@ -89,7 +89,7 @@ When implementing this class in PyTorch, you also need to specify the device typ :rtype: nn.Module .. py:function:: - xuanpolicy.torch.representations.cnn.AC_CNN_Atari._create_network() + xuance.torch.representations.cnn.AC_CNN_Atari._create_network() Create the convolutional neural netowrks for actor-critic based algorithms and Atari tasks. @@ -97,7 +97,7 @@ When implementing this class in PyTorch, you also need to specify the device typ :rtype: nn.Module .. py:function:: - xuanpolicy.torch.representations.cnn.AC_CNN_Atari.forward(observations) + xuance.torch.representations.cnn.AC_CNN_Atari.forward(observations) Calculate feature representation of the input observations. @@ -131,7 +131,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.representations import * + from xuance.torch.representations import * # process the input observations with stacks of CNN layers class Basic_CNN(nn.Module): diff --git a/docs/source/documents/api/representations/mlp.rst b/docs/source/documents/api/representations/mlp.rst index 91680b159..ecfa981c3 100644 --- a/docs/source/documents/api/representations/mlp.rst +++ b/docs/source/documents/api/representations/mlp.rst @@ -2,7 +2,7 @@ MLP-based ===================================== The Multi-Layer Perceptron (MLP) is one of the simplest deep neural network models used for processing vector inputs. -Users can instantiate the MLP module according to their own needs, which is defined in the `./xuanpolicy/torch/utils/layers.py`, `./xuanpolicy/tensorflow/utils/layers.py` and `./xuanpolicy/mindspore/utils/layers.py` files with the class name `mlp_block`. +Users can instantiate the MLP module according to their own needs, which is defined in the `./xuance/torch/utils/layers.py`, `./xuance/tensorflow/utils/layers.py` and `./xuance/mindspore/utils/layers.py` files with the class name `mlp_block`. To instantiate this class, you need to specify the input dimension (`input_dim`), output dimension (`output_dim`), normalization method (`normalize`), activation function choice (`activation`), and initialization method (`initialize`). @@ -15,7 +15,7 @@ When implementing this class in PyTorch, you also need to specify the device typ **PyTorch:** .. py:class:: - xuanpolicy.torch.representations.mlp.Basic_Identical(input_shape, device) + xuance.torch.representations.mlp.Basic_Identical(input_shape, device) :param input_shape: The shape of the inputs. :type input_shape: Sequence[int] @@ -23,7 +23,7 @@ When implementing this class in PyTorch, you also need to specify the device typ :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.representations.mlp.Basic_Identical.forward(observations) + xuance.torch.representations.mlp.Basic_Identical.forward(observations) Calculate feature representation of the input observations. @@ -33,7 +33,7 @@ When implementing this class in PyTorch, you also need to specify the device typ :rtype: dict .. py:class:: - xuanpolicy.torch.representations.mlp.Basic_MLP(input_shape, device) + xuance.torch.representations.mlp.Basic_MLP(input_shape, device) :param input_shape: The shape of the inputs. :type input_shape: Sequence[int] @@ -41,7 +41,7 @@ When implementing this class in PyTorch, you also need to specify the device typ :type device: str, int, torch.device .. py:function:: - xuanpolicy.torch.representations.mlp.Basic_MLP._create_network() + xuance.torch.representations.mlp.Basic_MLP._create_network() Create the multi-layer perceptron netowrks. @@ -49,7 +49,7 @@ When implementing this class in PyTorch, you also need to specify the device typ :rtype: nn.Module .. py:function:: - xuanpolicy.torch.representations.mlp.Basic_MLP.forward(observations) + xuance.torch.representations.mlp.Basic_MLP.forward(observations) Calculate feature representation of the input observations. @@ -83,7 +83,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.representations import * + from xuance.torch.representations import * # directly returns the original observation class Basic_Identical(nn.Module): diff --git a/docs/source/documents/api/representations/rnn.rst b/docs/source/documents/api/representations/rnn.rst index 45f27e255..a46bd842b 100644 --- a/docs/source/documents/api/representations/rnn.rst +++ b/docs/source/documents/api/representations/rnn.rst @@ -3,7 +3,7 @@ RNN-based Recurrent Neural Networks (RNNs) are mainly used for processing sequential signal information to extract feature vectors of the current sequence. Depending on the usage scenario, this software provides two types of RNN modules: `gru_block` and `lstm_block`. -Their definitions can be found in `./xuanpolicy/torch/utils/layers.py` , `./xuanpolicy/tensorflow/utils/layers.py` and `./xuanpolicy/mindspore/utils/layers.py` respectively. +Their definitions can be found in `./xuance/torch/utils/layers.py` , `./xuance/tensorflow/utils/layers.py` and `./xuance/mindspore/utils/layers.py` respectively. To instantiate these classes, you need to specify the input dimension (`input_dim`), output dimension (`output_dim`), pruning method (`dropout`), and initialization method (`initialize`). @@ -16,7 +16,7 @@ Similarly, when implementing these classes in PyTorch, you also need to specify **PyTorch:** .. py:class:: - xuanpolicy.torch.representations.rnn.Basic_RNN(input_shape, hidden_sizes, normalize=None, initialize=None, activation=None, device=None, kwargs) + xuance.torch.representations.rnn.Basic_RNN(input_shape, hidden_sizes, normalize=None, initialize=None, activation=None, device=None, kwargs) The ``hidden_sizes`` is a dict input, which contains "fc_hidden_sizes" and "fc_hidden_sizes". The "fc_hidden_sizes" is the sizes of the fully connected layers before rnn layers. @@ -43,7 +43,7 @@ Similarly, when implementing these classes in PyTorch, you also need to specify :type rnn: str .. py:function:: - xuanpolicy.torch.representations.rnn.Basic_RNN._create_network() + xuance.torch.representations.rnn.Basic_RNN._create_network() Create the recurrent neural netowrks. @@ -51,7 +51,7 @@ Similarly, when implementing these classes in PyTorch, you also need to specify :rtype: nn.Module, nn.Module, int .. py:function:: - xuanpolicy.torch.representations.rnn.Basic_RNN.forward(x, h, c=None) + xuance.torch.representations.rnn.Basic_RNN.forward(x, h, c=None) Calculate feature representation of the inputs. @@ -65,7 +65,7 @@ Similarly, when implementing these classes in PyTorch, you also need to specify :rtype: dict .. py:function:: - xuanpolicy.torch.representations.rnn.Basic_RNN.init_hidden(batch) + xuance.torch.representations.rnn.Basic_RNN.init_hidden(batch) Initialize a batch of RNN hidden states. @@ -75,7 +75,7 @@ Similarly, when implementing these classes in PyTorch, you also need to specify :rtype: torch.Tensor .. py:function:: - xuanpolicy.torch.representations.rnn.Basic_RNN.init_hidden_item(i, rnn_hidden) + xuance.torch.representations.rnn.Basic_RNN.init_hidden_item(i, rnn_hidden) Initialize a slice of hidden states from the given RNN hidden states. @@ -87,7 +87,7 @@ Similarly, when implementing these classes in PyTorch, you also need to specify :rtype: torch.Tensor .. py:function:: - xuanpolicy.torch.representations.rnn.Basic_RNN.get_hidden_item(i, rnn_hidden) + xuance.torch.representations.rnn.Basic_RNN.get_hidden_item(i, rnn_hidden) Get a slice of hidden states from the given RNN hidden states. @@ -123,7 +123,7 @@ Source Code .. code-block:: python - from xuanpolicy.torch.representations import * + from xuance.torch.representations import * class Basic_RNN(nn.Module): def __init__(self, diff --git a/docs/source/documents/benchmark/mujoco.rst b/docs/source/documents/benchmark/mujoco.rst index 0dc390440..2549e3c55 100644 --- a/docs/source/documents/benchmark/mujoco.rst +++ b/docs/source/documents/benchmark/mujoco.rst @@ -22,7 +22,7 @@ Results +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ | Task | | Ant | HalfCheetah | Hopper | Walker2d | Swimmer | Humanoid | Reacher | Ipendulum | IDPendulum | +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ -| DDPG | XuanPolicy | 1472.8 | 10093 | 3434.9 | 2443.7 | 67.7 | 99 | -4.05 | 1000 | 9359.8 | +| DDPG | XuanCe | 1472.8 | 10093 | 3434.9 | 2443.7 | 67.7 | 99 | -4.05 | 1000 | 9359.8 | +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ | | Tianshou | 990.4 | 11718.7 | 2197 | 1400.6 | 144.1 | 177.3 | -3.3 | 1000 | 8364.3 | +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ @@ -30,7 +30,7 @@ Results +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ | | SpinningUp | 840 | 11000 | 1800 | 1950 | 137 | / | / | / | / | +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ -| TD3 | XuanPolicy | 4822.9 | 10718.1 | 3492.4 | 4307.9 | 59.9 | 547.88 | -4.07 | 1000 | 9358.9 | +| TD3 | XuanCe | 4822.9 | 10718.1 | 3492.4 | 4307.9 | 59.9 | 547.88 | -4.07 | 1000 | 9358.9 | +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ | | Tianshou | 5116.4 | 10201.2 | 3472.2 | 3982.4 | 104.2 | 5189.5 | -2.7 | 1000 | 9349.2 | +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ @@ -38,13 +38,13 @@ Results +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ | | SpinningUp | 3800 | 9750 | 2860 | 4000 | 78 | / | / | / | / | +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ -| A2C | XuanPolicy | 1420.4 | 2674.5 | 825.9 | 970.6 | 51.4 | 240.9 | -11.7 | 1000 | 9357.8 | +| A2C | XuanCe | 1420.4 | 2674.5 | 825.9 | 970.6 | 51.4 | 240.9 | -11.7 | 1000 | 9357.8 | +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ | | Tianshou | 3485.4 | 1829.9 | 1253.2 | 1091.6 | 36.6 | 1726 | -6.7 | 1000 | 9257.7 | +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ | | Published | / | 1000 | 900 | 850 | 31 | / | -24 | 1000 | 8100 | +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ -| PPO | XuanPolicy | 2810.7 | 4628.4 | 3450.1 | 4318.6 | 108.9 | 705.5 | -8.1 | 1000 | 9359.1 | +| PPO | XuanCe | 2810.7 | 4628.4 | 3450.1 | 4318.6 | 108.9 | 705.5 | -8.1 | 1000 | 9359.1 | +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ | | Tianshou | 3258.4 | 5783.9 | 2609.3 | 3588.5 | 66.7 | 787.1 | -4.1 | 1000 | 9231.3 | +------+------------+--------+-------------+--------+----------+---------+----------+---------+-----------+------------+ diff --git a/docs/source/documents/usage/basic_usage.rst b/docs/source/documents/usage/basic_usage.rst index 9428055da..63d33c1ec 100644 --- a/docs/source/documents/usage/basic_usage.rst +++ b/docs/source/documents/usage/basic_usage.rst @@ -8,13 +8,13 @@ Quick Start Run a DRL example ----------------------- -In XuanPolicy, it is easy to build a DRL agent. First you need to create a *runner* +In XuanCe, it is easy to build a DRL agent. First you need to create a *runner* and specify the ``agent_name``, ``env_name``, then a runner that contains agent, policy, and envs, etc., will be built. Finally, execute ``runner.run`` and the agent's model is training. .. code-block:: python - import xuanpolicy as xp + import xuance as xp runner = xp.get_runner(method='dqn', env='classic_control', env_id='CartPole-v1', @@ -30,12 +30,12 @@ After training the agent, you can test and view the model by the following codes Run an MARL example ----------------------- -XuanPolicy support MARL algorithms with both cooperative and competitive tasks. +XuanCe support MARL algorithms with both cooperative and competitive tasks. Similaly, you can start by: .. code-block:: python - import xuanpolicy as xp + import xuance as xp runner = xp.get_runner(method='maddpg', env='mpe', env_id='simple_spread_v3', @@ -46,7 +46,7 @@ For competitve tasks in which agents can be divided to two or more sides, you ca .. code-block:: python - import xuanpolicy as xp + import xuance as xp runner = xp.get_runner(method=["maddpg", "iddpg"], env='mpe', env_id='simple_push_v3', @@ -59,12 +59,12 @@ The "adversary"s are MADDPG agents, and the "agent"s are IDDPG agents. Test ----------------------- -After completing the algorithm training, XuanPolicy will save the model files and training log information in the designated directory. +After completing the algorithm training, XuanCe will save the model files and training log information in the designated directory. Users can specify "is_test=True" to perform testing. .. code-block:: python - import xuanpolicy as xp + import xuance as xp runner = xp.get_runner(method='dqn', env_name='classic_control', env_id='CartPole-v1', @@ -76,7 +76,7 @@ In the above code, "runner.benchmark()" can also be used instead of "runner.run( Logger ----------------------- -You can use the tensorboard or wandb to visualize the training process by specifying the "logger" parameter in the "xuanpolicy/configs/basic.yaml". +You can use the tensorboard or wandb to visualize the training process by specifying the "logger" parameter in the "xuance/configs/basic.yaml". .. code-block:: yaml @@ -101,7 +101,7 @@ Taking the path "./logs/dqn/torch/CartPole-v0" as an example, users can visualiz **2. W&B** If you choose to use the wandb tool for training visualization, -you can create an account according to the official W&B instructions and specify the username "wandb_user_name" in the "xuanpolicy/configs/basic.yaml" file. +you can create an account according to the official W&B instructions and specify the username "wandb_user_name" in the "xuance/configs/basic.yaml" file. For information on using W&B and its local deployment, you can refer to the following link: diff --git a/docs/source/documents/usage/installation.rst b/docs/source/documents/usage/installation.rst index f52911bbd..9d2b6d691 100644 --- a/docs/source/documents/usage/installation.rst +++ b/docs/source/documents/usage/installation.rst @@ -3,10 +3,10 @@ Installation The library can be run at Linux, Windows, MacOS, and EulerOS, etc. It is easy to be installed. -Before installing **XuanPolicy**, you should install Anaconda_ to prepare a python environment. +Before installing **XuanCe**, you should install Anaconda_ to prepare a python environment. -After that, open a terminal and install **XuanPolicy** by the following steps. -You can choose two ways to install XuanPolicy. +After that, open a terminal and install **XuanCe** by the following steps. +You can choose two ways to install XuanCe. .. raw:: html @@ -31,38 +31,38 @@ Install via PyPI .. code-block:: bash - pip install xuanpolicy + pip install xuance This command does not include the dependencies of deep learning toolboxes. -You can also install the **XuanPolicy** with PyTorch_, TensorFlow2_, MindSpore_, or all of them. +You can also install the **XuanCe** with PyTorch_, TensorFlow2_, MindSpore_, or all of them. .. code-block:: bash - pip install xuanpolicy[torch] + pip install xuance[torch] or .. code-block:: bash - pip install xuanpolicy[tensorflow] + pip install xuance[tensorflow] or .. code-block:: bash - pip install xuanpolicy[mindspore] + pip install xuance[mindspore] or .. code-block:: bash - pip install xuanpolicy[all] + pip install xuance[all] Install from GitHub repository --------------------------------------------- -Alternatively, you can install XuanPolicy from its GitHub repository. +Alternatively, you can install XuanCe from its GitHub repository. .. note:: @@ -80,19 +80,19 @@ Alternatively, you can install XuanPolicy from its GitHub repository. conda activate xpolicy -**Step 3**: Download the source code of XuanPolicy from GitHub. +**Step 3**: Download the source code of XuanCe from GitHub. .. code-block:: bash - git clone https://github.com/agi-brain/xuanpolicy.git + git clone https://github.com/agi-brain/xuance.git -**Step 4**: Change directory to the xuanpolicy. +**Step 4**: Change directory to the xuance. .. code-block:: bash - cd xuanpolicy + cd xuance -**Step 5**: Install xuanpolicy. +**Step 5**: Install xuance. .. code-block:: bash @@ -114,13 +114,13 @@ Alternatively, you can install XuanPolicy from its GitHub repository. Testing whether the installation was successful -------------------------------------------------------------------- -After installing XuanPolicy, you can enter the Python runtime environment by typing "python" in the terminal. -Then, test the installation of xuanpolicy by typing: +After installing XuanCe, you can enter the Python runtime environment by typing "python" in the terminal. +Then, test the installation of xuance by typing: .. code-block:: python - import xuanpolicy + import xuance -If no error or warning messages are displayed, it indicates that XuanPolicy has been successfully installed. +If no error or warning messages are displayed, it indicates that XuanCe has been successfully installed. You can proceed to the next step and start using it. diff --git a/docs/source/documents/usage/professional_usage.rst b/docs/source/documents/usage/professional_usage.rst index 89595ee07..63bc42854 100644 --- a/docs/source/documents/usage/professional_usage.rst +++ b/docs/source/documents/usage/professional_usage.rst @@ -2,7 +2,7 @@ Professional Usage ================================ The previous page demonstrated how to directly run an algorithm by calling the runner. -In order to help users better understand the internal implementation process of "XuanPolicy", +In order to help users better understand the internal implementation process of "XuanCe", and facilitate further algorithm development and implementation of their own reinforcement learning tasks, this section will take the PPO algorithm training on the MuJoCo environment task as an example, and provide a detailed introduction on how to call the API from the bottom level to implement reinforcement learning model training. @@ -20,7 +20,7 @@ Here we show a config file named "mujoco.yaml" for MuJoCo environment in gym. .. code-block:: yaml dl_toolbox: "torch" # The deep learning toolbox. Choices: "torch", "mindspore", "tensorlayer" - project_name: "XuanPolicy_Benchmark" + project_name: "XuanCe_Benchmark" logger: "tensorboard" # Choices: tensorboard, wandb. wandb_user_name: "your_user_name" render: False @@ -89,7 +89,7 @@ which uses the Python package `argparser` to read the command line instructions import argparser def parse_args(): - parser = argparse.ArgumentParser("Example of XuanPolicy.") + parser = argparse.ArgumentParser("Example of XuanCe.") parser.add_argument("--method", type=str, default="ppo") parser.add_argument("--env", type=str, default="mujoco") parser.add_argument("--env-id", type=str, default="InvertedPendulum-v4") @@ -107,7 +107,7 @@ and then the configuration parameters from Step 1 are obtained. .. code-block:: python - from xuanpolicy import get_arguments + from xuance import get_arguments if __name__ == "__main__": parser = parse_args() @@ -118,8 +118,8 @@ and then the configuration parameters from Step 1 are obtained. parser_args=parser) run(args) -In this step, the ``get_arguments()`` function from "XuanPolicy" is called. -In this function, it first searches for readable parameters based on the combination of the ``env`` and ``env_id`` variables in the `xuanpolicy/configs/` directory. +In this step, the ``get_arguments()`` function from "XuanCe" is called. +In this function, it first searches for readable parameters based on the combination of the ``env`` and ``env_id`` variables in the `xuance/configs/` directory. If default parameters already exist, they are all read. Then, the function continues to index the configuration file from Step 1 using the ``config.path`` path and reads all the parameters from the .yaml file. Finally, it reads all the parameters from the ``parser``. @@ -145,10 +145,10 @@ Here is an example definition of the run() function with comments: import numpy as np import torch.optim - from xuanpolicy.common import space2shape - from xuanpolicy.environment import make_envs - from xuanpolicy.torch.utils.operations import set_seed - from xuanpolicy.torch.utils import ActivationFunctions + from xuance.common import space2shape + from xuance.environment import make_envs + from xuance.torch.utils.operations import set_seed + from xuance.torch.utils import ActivationFunctions def run(args): agent_name = args.agent # get the name of Agent. @@ -165,7 +165,7 @@ Here is an example definition of the run() function with comments: n_envs = envs.num_envs # get the number of vectorized environments. # prepare representation - from xuanpolicy.torch.representations import Basic_MLP + from xuance.torch.representations import Basic_MLP representation = Basic_MLP(input_shape=space2shape(args.observation_space), hidden_sizes=args.representation_hidden_size, normalize=None, @@ -174,7 +174,7 @@ Here is an example definition of the run() function with comments: device=args.device) # create representation # prepare policy - from xuanpolicy.torch.policies import Gaussian_AC_Policy + from xuance.torch.policies import Gaussian_AC_Policy policy = Gaussian_AC_Policy(action_space=args.action_space, representation=representation, actor_hidden_size=args.actor_hidden_size, @@ -185,7 +185,7 @@ Here is an example definition of the run() function with comments: device=args.device) # create Gaussian policy # prepare agent - from xuanpolicy.torch.agents import PPOCLIP_Agent, get_total_iters + from xuance.torch.agents import PPOCLIP_Agent, get_total_iters optimizer = torch.optim.Adam(policy.parameters(), args.learning_rate, eps=1e-5) # create optimizer lr_scheduler = torch.optim.lr_scheduler.LinearLR(optimizer, start_factor=1.0, end_factor=0.0, total_iters=get_total_iters(agent_name, args)) # for learning rate decay @@ -256,6 +256,6 @@ After finishing the above three steps, you can run the `python_mujoco.py` file i The source code of this example can be visited at the following link: -`https://github.com/agi-brain/xuanpolicy/examples/ppo/ppo_mujoco.py `_ +`https://github.com/agi-brain/xuance/examples/ppo/ppo_mujoco.py `_ diff --git a/docs/source/index.rst b/docs/source/index.rst index c755cf3df..c5cec002d 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -1,12 +1,12 @@ -.. XuanPolicy documentation master file, created by +.. XuanCe documentation master file, created by sphinx-quickstart on Wed May 31 20:18:19 2023. You can adapt this file completely to your liking, but it should at least contain the root `toctree` directive. -Welcome to XuanPolicy's documentation! +Welcome to XuanCe's documentation! ====================================== -**XuanPolicy** is an open-source ensemble of Deep Reinforcement Learning (DRL) algorithm implementations. +**XuanCe** is an open-source ensemble of Deep Reinforcement Learning (DRL) algorithm implementations. We call it as **Xuan-Ce (玄策)** in Chinese. "**Xuan (玄)**" means incredible and magic box, "**Ce (策)**" means policy. @@ -26,10 +26,10 @@ and hope it can really become a zoo full of DRL algorithms. .. _TensorFlow: https://www.tensorflow.org/ .. _MindSpore: https://www.mindspore.cn/en -Currently, THe XuanPolicy has been open-sourced on GitHub and OpenI: +Currently, THe XuanCe has been open-sourced on GitHub and OpenI: -| **GitHub**： `https://github.com/agi-brain/xuanpolicy.git `_ -| **OpenI**： `https://github.com/agi-brain/xuanpolicy.git `_ +| **GitHub**： `https://github.com/agi-brain/xuance.git `_ +| **OpenI**： `https://github.com/agi-brain/xuance.git `_ .. raw:: html diff --git a/example_ddpg.py b/example_ddpg.py index 76d9bee6a..7f153a2ee 100644 --- a/example_ddpg.py +++ b/example_ddpg.py @@ -5,15 +5,15 @@ import torch.optim import wandb -from xuanpolicy import get_arguments -from xuanpolicy.environment import make_envs -from xuanpolicy.torch.utils.operations import set_seed -from xuanpolicy.torch.utils.input_reformat import get_repre_in, get_policy_in -from xuanpolicy.torch.agents import get_total_iters +from xuance import get_arguments +from xuance.environment import make_envs +from xuance.torch.utils.operations import set_seed +from xuance.torch.utils.input_reformat import get_repre_in, get_policy_in +from xuance.torch.agents import get_total_iters def parse_args(): - parser = argparse.ArgumentParser("Example of XuanPolicy.") + parser = argparse.ArgumentParser("Example of XuanCe.") parser.add_argument("--method", type=str, default="ddpg") parser.add_argument("--env", type=str, default="classic_control") parser.add_argument("--env-id", type=str, default="Pendulum-v1") @@ -36,12 +36,12 @@ def run(args): n_envs = envs.num_envs # prepare representation - from xuanpolicy.torch.representations import REGISTRY as REGISTRY_Representation + from xuance.torch.representations import REGISTRY as REGISTRY_Representation input_representation = get_repre_in(args) representation = REGISTRY_Representation[args.representation](*input_representation) # prepare policy - from xuanpolicy.torch.policies import REGISTRY as REGISTRY_Policy + from xuance.torch.policies import REGISTRY as REGISTRY_Policy input_policy = get_policy_in(args, representation) policy = REGISTRY_Policy[args.policy](*input_policy) @@ -52,7 +52,7 @@ def run(args): total_iters=get_total_iters(agent_name, args)) critic_lr_scheduler = torch.optim.lr_scheduler.LinearLR(critic_optimizer, start_factor=1.0, end_factor=0.25, total_iters=get_total_iters(agent_name, args)) - from xuanpolicy.torch.agents import REGISTRY as REGISTRY_Agent + from xuance.torch.agents import REGISTRY as REGISTRY_Agent agent = REGISTRY_Agent[agent_name](args, envs, policy, [actor_optimizer, critic_optimizer], [actor_lr_scheduler, critic_lr_scheduler], diff --git a/examples/ddpg/ddpg_mujoco.py b/examples/ddpg/ddpg_mujoco.py index 5a6b66bb7..5a180b409 100644 --- a/examples/ddpg/ddpg_mujoco.py +++ b/examples/ddpg/ddpg_mujoco.py @@ -4,15 +4,15 @@ import numpy as np import torch.optim -from xuanpolicy import get_arguments -from xuanpolicy.common import space2shape -from xuanpolicy.environment import make_envs -from xuanpolicy.torch.utils.operations import set_seed -from xuanpolicy.torch.utils import ActivationFunctions +from xuance import get_arguments +from xuance.common import space2shape +from xuance.environment import make_envs +from xuance.torch.utils.operations import set_seed +from xuance.torch.utils import ActivationFunctions def parse_args(): - parser = argparse.ArgumentParser("Example of XuanPolicy.") + parser = argparse.ArgumentParser("Example of XuanCe.") parser.add_argument("--method", type=str, default="ddpg") parser.add_argument("--env", type=str, default="mujoco") parser.add_argument("--env-id", type=str, default="InvertedPendulum-v4") @@ -39,12 +39,12 @@ def run(args): n_envs = envs.num_envs # prepare the Representation - from xuanpolicy.torch.representations import Basic_Identical + from xuance.torch.representations import Basic_Identical representation = Basic_Identical(input_shape=space2shape(args.observation_space), device=args.device) # prepare the Policy - from xuanpolicy.torch.policies import DDPGPolicy + from xuance.torch.policies import DDPGPolicy policy = DDPGPolicy(action_space=args.action_space, representation=representation, actor_hidden_size=args.actor_hidden_size, @@ -54,7 +54,7 @@ def run(args): device=args.device) # prepare the Agent - from xuanpolicy.torch.agents import DDPG_Agent, get_total_iters + from xuance.torch.agents import DDPG_Agent, get_total_iters actor_optimizer = torch.optim.Adam(policy.actor.parameters(), args.actor_learning_rate) critic_optimizer = torch.optim.Adam(policy.critic.parameters(), args.critic_learning_rate) actor_lr_scheduler = torch.optim.lr_scheduler.LinearLR(actor_optimizer, start_factor=1.0, end_factor=0.25, diff --git a/examples/ddpg/ddpg_mujoco_config.yaml b/examples/ddpg/ddpg_mujoco_config.yaml index a54e065cd..c80e7ea2e 100644 --- a/examples/ddpg/ddpg_mujoco_config.yaml +++ b/examples/ddpg/ddpg_mujoco_config.yaml @@ -1,5 +1,5 @@ dl_toolbox: "torch" # The deep learning toolbox. Choices: "torch", "mindspore", "tensorlayer" -project_name: "XuanPolicy_Benchmark" +project_name: "XuanCe_Benchmark" logger: "tensorboard" # Choices: tensorboard, wandb. wandb_user_name: "your_user_name" render: False diff --git a/examples/dqn/dqn_atari.py b/examples/dqn/dqn_atari.py index 77931f0e8..a7ffb3053 100644 --- a/examples/dqn/dqn_atari.py +++ b/examples/dqn/dqn_atari.py @@ -4,15 +4,15 @@ import numpy as np import torch.optim -from xuanpolicy import get_arguments -from xuanpolicy.common import space2shape -from xuanpolicy.environment import make_envs -from xuanpolicy.torch.utils.operations import set_seed -from xuanpolicy.torch.utils import ActivationFunctions +from xuance import get_arguments +from xuance.common import space2shape +from xuance.environment import make_envs +from xuance.torch.utils.operations import set_seed +from xuance.torch.utils import ActivationFunctions def parse_args(): - parser = argparse.ArgumentParser("Example of XuanPolicy.") + parser = argparse.ArgumentParser("Example of XuanCe.") parser.add_argument("--method", type=str, default="dqn") parser.add_argument("--env", type=str, default="atari") parser.add_argument("--env-id", type=str, default="ALE/Breakout-v5") @@ -39,7 +39,7 @@ def run(args): n_envs = envs.num_envs # prepare representation - from xuanpolicy.torch.representations import Basic_CNN + from xuance.torch.representations import Basic_CNN representation = Basic_CNN(input_shape=space2shape(args.observation_space), kernels=args.kernels, strides=args.strides, @@ -50,7 +50,7 @@ def run(args): device=args.device) # prepare policy - from xuanpolicy.torch.policies import BasicQnetwork + from xuance.torch.policies import BasicQnetwork policy = BasicQnetwork(action_space=args.action_space, representation=representation, hidden_size=args.q_hidden_size, @@ -60,7 +60,7 @@ def run(args): device=args.device) # prepare agent - from xuanpolicy.torch.agents import DQN_Agent, get_total_iters + from xuance.torch.agents import DQN_Agent, get_total_iters optimizer = torch.optim.Adam(policy.parameters(), args.learning_rate, eps=1e-5) lr_scheduler = torch.optim.lr_scheduler.LinearLR(optimizer, start_factor=1.0, end_factor=0.0, total_iters=get_total_iters(agent_name, args)) diff --git a/examples/dqn/dqn_atari_config.yaml b/examples/dqn/dqn_atari_config.yaml index f208f52f8..e957f281b 100644 --- a/examples/dqn/dqn_atari_config.yaml +++ b/examples/dqn/dqn_atari_config.yaml @@ -1,5 +1,5 @@ dl_toolbox: "torch" # The deep learning toolbox. Choices: "torch", "mindspore", "tensorlayer" -project_name: "XuanPolicy_Benchmark" +project_name: "XuanCe_Benchmark" logger: "tensorboard" # Choices: tensorboard, wandb. wandb_user_name: "your_user_name" render: False diff --git a/examples/ppo/ppo_atari.py b/examples/ppo/ppo_atari.py index 4b79d39c2..bcaca10ba 100644 --- a/examples/ppo/ppo_atari.py +++ b/examples/ppo/ppo_atari.py @@ -4,15 +4,15 @@ import numpy as np import torch.optim -from xuanpolicy import get_arguments -from xuanpolicy.common import space2shape -from xuanpolicy.environment import make_envs -from xuanpolicy.torch.utils.operations import set_seed -from xuanpolicy.torch.utils import ActivationFunctions +from xuance import get_arguments +from xuance.common import space2shape +from xuance.environment import make_envs +from xuance.torch.utils.operations import set_seed +from xuance.torch.utils import ActivationFunctions def parse_args(): - parser = argparse.ArgumentParser("Example of XuanPolicy.") + parser = argparse.ArgumentParser("Example of XuanCe.") parser.add_argument("--method", type=str, default="ppo") parser.add_argument("--env", type=str, default="atari") parser.add_argument("--env-id", type=str, default="ALE/Breakout-v5") @@ -39,7 +39,7 @@ def run(args): n_envs = envs.num_envs # prepare representation - from xuanpolicy.torch.representations import AC_CNN_Atari + from xuance.torch.representations import AC_CNN_Atari representation = AC_CNN_Atari(input_shape=space2shape(args.observation_space), kernels=args.kernels, strides=args.strides, @@ -51,7 +51,7 @@ def run(args): fc_hidden_sizes=args.fc_hidden_sizes) # prepare policy - from xuanpolicy.torch.policies import Categorical_AC_Policy + from xuance.torch.policies import Categorical_AC_Policy policy = Categorical_AC_Policy(action_space=args.action_space, representation=representation, actor_hidden_size=args.actor_hidden_size, @@ -62,7 +62,7 @@ def run(args): device=args.device) # prepare agent - from xuanpolicy.torch.agents import PPOCLIP_Agent, get_total_iters + from xuance.torch.agents import PPOCLIP_Agent, get_total_iters optimizer = torch.optim.Adam(policy.parameters(), args.learning_rate, eps=1e-5) lr_scheduler = torch.optim.lr_scheduler.LinearLR(optimizer, start_factor=1.0, end_factor=0.0, total_iters=get_total_iters(agent_name, args)) diff --git a/examples/ppo/ppo_atari_config.yaml b/examples/ppo/ppo_atari_config.yaml index bc034ae16..c9bd95e99 100644 --- a/examples/ppo/ppo_atari_config.yaml +++ b/examples/ppo/ppo_atari_config.yaml @@ -1,5 +1,5 @@ dl_toolbox: "torch" # The deep learning toolbox. Choices: "torch", "mindspore", "tensorlayer" -project_name: "XuanPolicy_Benchmark" +project_name: "XuanCe_Benchmark" logger: "tensorboard" # Choices: tensorboard, wandb. wandb_user_name: "your_user_name" render: False diff --git a/examples/ppo/ppo_mujoco.py b/examples/ppo/ppo_mujoco.py index 6a61d8552..f7b09a0ef 100644 --- a/examples/ppo/ppo_mujoco.py +++ b/examples/ppo/ppo_mujoco.py @@ -4,15 +4,15 @@ import numpy as np import torch.optim -from xuanpolicy import get_arguments -from xuanpolicy.common import space2shape -from xuanpolicy.environment import make_envs -from xuanpolicy.torch.utils.operations import set_seed -from xuanpolicy.torch.utils import ActivationFunctions +from xuance import get_arguments +from xuance.common import space2shape +from xuance.environment import make_envs +from xuance.torch.utils.operations import set_seed +from xuance.torch.utils import ActivationFunctions def parse_args(): - parser = argparse.ArgumentParser("Example of XuanPolicy.") + parser = argparse.ArgumentParser("Example of XuanCe.") parser.add_argument("--method", type=str, default="ppo") parser.add_argument("--env", type=str, default="mujoco") parser.add_argument("--env-id", type=str, default="InvertedPendulum-v4") @@ -39,7 +39,7 @@ def run(args): n_envs = envs.num_envs # prepare representation - from xuanpolicy.torch.representations import Basic_MLP + from xuance.torch.representations import Basic_MLP representation = Basic_MLP(input_shape=space2shape(args.observation_space), hidden_sizes=args.representation_hidden_size, normalize=None, @@ -48,7 +48,7 @@ def run(args): device=args.device) # prepare policy - from xuanpolicy.torch.policies import Gaussian_AC_Policy + from xuance.torch.policies import Gaussian_AC_Policy policy = Gaussian_AC_Policy(action_space=args.action_space, representation=representation, actor_hidden_size=args.actor_hidden_size, @@ -59,7 +59,7 @@ def run(args): device=args.device) # prepare agent - from xuanpolicy.torch.agents import PPOCLIP_Agent, get_total_iters + from xuance.torch.agents import PPOCLIP_Agent, get_total_iters optimizer = torch.optim.Adam(policy.parameters(), args.learning_rate, eps=1e-5) lr_scheduler = torch.optim.lr_scheduler.LinearLR(optimizer, start_factor=1.0, end_factor=0.0, total_iters=get_total_iters(agent_name, args)) diff --git a/examples/ppo/ppo_mujoco_config.yaml b/examples/ppo/ppo_mujoco_config.yaml index 709859e26..f7b511026 100644 --- a/examples/ppo/ppo_mujoco_config.yaml +++ b/examples/ppo/ppo_mujoco_config.yaml @@ -1,5 +1,5 @@ dl_toolbox: "torch" # The deep learning toolbox. Choices: "torch", "mindspore", "tensorlayer" -project_name: "XuanPolicy_Benchmark" +project_name: "XuanCe_Benchmark" logger: "tensorboard" # Choices: tensorboard, wandb. wandb_user_name: "your_user_name" render: False diff --git a/setup.py b/setup.py index 90cc8008d..6e7761ab4 100644 --- a/setup.py +++ b/setup.py @@ -1,10 +1,10 @@ from setuptools import find_packages, setup setup( - name='xuanpolicy', - packages=find_packages(include=['xuanpolicy', 'xuanpolicy.*']), + name='xuance', + packages=find_packages(include=['xuance', 'xuance.*']), package_data={ - "xuanpolicy": + "xuance": [ "configs/*.yaml", "configs/*/*.yaml", @@ -13,13 +13,13 @@ "environment/magent2/magent.dll" # for magent2 environment ] }, - version='0.1.11.3', - description='XuanPolicy: A Comprehensive and Unified Deep Reinforcement Learning Library.', - author='XuanPolicy contributors.', + version='1.0.0', + description='XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library.', + author='XuanCe contributors.', author_email='', license='MIT', url='', - download_url='https://github.com/agi-brain/xuanpolicy.git', + download_url='https://github.com/agi-brain/xuance.git', keywords=['deep reinforcement learning', 'software library', 'PyTorch', 'TensorFlow2', 'MindSpore'], classifiers=[ 'Development Status :: 4 - Beta', diff --git a/tests/demo_a2c.py b/tests/demo_a2c.py index 00705c3d9..c2079e8ea 100644 --- a/tests/demo_a2c.py +++ b/tests/demo_a2c.py @@ -1,12 +1,12 @@ ''' -Repo: XuanPolicy +Repo: XuanCe Example for single agent DRL: $ python main.py --method dqn --env-name toy_env/CartPole-v0 ''' import argparse -from xuanpolicy import get_runner +from xuance import get_runner def parse_args(): diff --git a/xuance/__init__.py b/xuance/__init__.py new file mode 100644 index 000000000..18731c152 --- /dev/null +++ b/xuance/__init__.py @@ -0,0 +1,5 @@ +from xuance import common, environment, configs +from xuance import tensorflow, mindspore, torch +from xuance.common.common_tools import get_runner, get_arguments + +__version__ = '0.1.11' \ No newline at end of file diff --git a/xuance/common/__init__.py b/xuance/common/__init__.py new file mode 100644 index 000000000..77ca16dfe --- /dev/null +++ b/xuance/common/__init__.py @@ -0,0 +1,5 @@ +from xuance.common.common_tools import * +from xuance.common.statistic_tools import * +from xuance.common.memory_tools import * +from xuance.common.memory_tools_marl import * +from xuance.common.segtree_tool import * diff --git a/xuanpolicy/common/common_tools.py b/xuance/common/common_tools.py similarity index 94% rename from xuanpolicy/common/common_tools.py rename to xuance/common/common_tools.py index 6f9c72811..d200d737c 100644 --- a/xuanpolicy/common/common_tools.py +++ b/xuance/common/common_tools.py @@ -34,17 +34,17 @@ def get_arguments(method, env, env_id, config_path=None, parser_args=None): Get arguments from .yaml files method: the algorithm name that will be implemented, env: env/scenario, e.g., classic/CartPole-v0, - config_path: default is None, if None, the default configs (xuanpolicy/configs/.../*.yaml) will be loaded. + config_path: default is None, if None, the default configs (xuance/configs/.../*.yaml) will be loaded. parser_args: arguments that specified by parser tools. """ main_path = os.getcwd() main_path_package = os.path.dirname(os.path.dirname(__file__)) config_path_default = os.path.join(main_path_package, "configs") - ''' get the arguments from xuanpolicy/config/basic.yaml ''' + ''' get the arguments from xuance/config/basic.yaml ''' config_basic = get_config(os.path.join(config_path_default, "basic.yaml")) - ''' get the arguments from xuanpolicy/config/agent/env/scenario.yaml ''' + ''' get the arguments from xuance/config/agent/env/scenario.yaml ''' if env in ["atari", "mujoco"]: file_name = env + ".yaml" else: @@ -93,7 +93,7 @@ def get_runner(method, This method returns a runner that specified by the users according to the inputs: method: the algorithm name that will be implemented, env: env/scenario, e.g., classic/CartPole-v0, - config_path: default is None, if None, the default configs (xuanpolicy/configs/.../*.yaml) will be loaded. + config_path: default is None, if None, the default configs (xuance/configs/.../*.yaml) will be loaded. parser_args: arguments that specified by parser tools. is_test: default is False, if True, it will load the models and run the environment with rendering. """ @@ -104,10 +104,10 @@ def get_runner(method, print("Calculating device:", device) if dl_toolbox == "torch": - from xuanpolicy.torch.runners import REGISTRY as run_REGISTRY + from xuance.torch.runners import REGISTRY as run_REGISTRY print("Deep learning toolbox: PyTorch.") elif dl_toolbox == "mindspore": - from xuanpolicy.mindspore.runners import REGISTRY as run_REGISTRY + from xuance.mindspore.runners import REGISTRY as run_REGISTRY from mindspore import context print("Deep learning toolbox: MindSpore.") if device != "Auto": @@ -118,7 +118,7 @@ def get_runner(method, context.set_context(mode=context.GRAPH_MODE) # 静态图（断点无法进入） # context.set_context(mode=context.PYNATIVE_MODE) # 动态图（便于调试） elif dl_toolbox == "tensorflow": - from xuanpolicy.tensorflow.runners import REGISTRY as run_REGISTRY + from xuance.tensorflow.runners import REGISTRY as run_REGISTRY print("Deep learning toolbox: TensorFlow.") if device in ["cpu", "CPU"]: os.environ["CUDA_VISIBLE_DEVICES"] = "-1" diff --git a/xuanpolicy/common/memory_tools.py b/xuance/common/memory_tools.py similarity index 99% rename from xuanpolicy/common/memory_tools.py rename to xuance/common/memory_tools.py index c55a77126..f5daad316 100644 --- a/xuanpolicy/common/memory_tools.py +++ b/xuance/common/memory_tools.py @@ -3,8 +3,8 @@ from gym import Space from abc import ABC, abstractmethod from typing import Optional, Union -from xuanpolicy.common import space2shape, discount_cumsum -from xuanpolicy.common.segtree_tool import SumSegmentTree, MinSegmentTree +from xuance.common import space2shape, discount_cumsum +from xuance.common.segtree_tool import SumSegmentTree, MinSegmentTree from collections import deque from typing import Dict diff --git a/xuanpolicy/common/memory_tools_marl.py b/xuance/common/memory_tools_marl.py similarity index 99% rename from xuanpolicy/common/memory_tools_marl.py rename to xuance/common/memory_tools_marl.py index df07267d2..9b2240248 100644 --- a/xuanpolicy/common/memory_tools_marl.py +++ b/xuance/common/memory_tools_marl.py @@ -1,6 +1,6 @@ import numpy as np from abc import ABC, abstractmethod -from xuanpolicy.common.common_tools import discount_cumsum +from xuance.common.common_tools import discount_cumsum class BaseBuffer(ABC): diff --git a/xuanpolicy/common/segtree_tool.py b/xuance/common/segtree_tool.py similarity index 100% rename from xuanpolicy/common/segtree_tool.py rename to xuance/common/segtree_tool.py diff --git a/xuanpolicy/common/statistic_tools.py b/xuance/common/statistic_tools.py similarity index 100% rename from xuanpolicy/common/statistic_tools.py rename to xuance/common/statistic_tools.py diff --git a/xuanpolicy/configs/__init__.py b/xuance/configs/__init__.py similarity index 100% rename from xuanpolicy/configs/__init__.py rename to xuance/configs/__init__.py diff --git a/xuanpolicy/configs/a2c/atari.yaml b/xuance/configs/a2c/atari.yaml similarity index 100% rename from xuanpolicy/configs/a2c/atari.yaml rename to xuance/configs/a2c/atari.yaml diff --git a/xuanpolicy/configs/a2c/box2d/BipedalWalker-v3.yaml b/xuance/configs/a2c/box2d/BipedalWalker-v3.yaml similarity index 100% rename from xuanpolicy/configs/a2c/box2d/BipedalWalker-v3.yaml rename to xuance/configs/a2c/box2d/BipedalWalker-v3.yaml diff --git a/xuanpolicy/configs/a2c/box2d/LunarLander-v2.yaml b/xuance/configs/a2c/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/a2c/box2d/LunarLander-v2.yaml rename to xuance/configs/a2c/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/a2c/classic_control/Acrobot-v1.yaml b/xuance/configs/a2c/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/a2c/classic_control/Acrobot-v1.yaml rename to xuance/configs/a2c/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/a2c/classic_control/CartPole-v1.yaml b/xuance/configs/a2c/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/a2c/classic_control/CartPole-v1.yaml rename to xuance/configs/a2c/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/a2c/classic_control/MountainCar-v0.yaml b/xuance/configs/a2c/classic_control/MountainCar-v0.yaml similarity index 100% rename from xuanpolicy/configs/a2c/classic_control/MountainCar-v0.yaml rename to xuance/configs/a2c/classic_control/MountainCar-v0.yaml diff --git a/xuanpolicy/configs/a2c/classic_control/Pendulum-v1.yaml b/xuance/configs/a2c/classic_control/Pendulum-v1.yaml similarity index 100% rename from xuanpolicy/configs/a2c/classic_control/Pendulum-v1.yaml rename to xuance/configs/a2c/classic_control/Pendulum-v1.yaml diff --git a/xuanpolicy/configs/a2c/mujoco.yaml b/xuance/configs/a2c/mujoco.yaml similarity index 100% rename from xuanpolicy/configs/a2c/mujoco.yaml rename to xuance/configs/a2c/mujoco.yaml diff --git a/xuanpolicy/configs/basic.yaml b/xuance/configs/basic.yaml similarity index 92% rename from xuanpolicy/configs/basic.yaml rename to xuance/configs/basic.yaml index 3a5f77791..b46f093aa 100644 --- a/xuanpolicy/configs/basic.yaml +++ b/xuance/configs/basic.yaml @@ -1,6 +1,6 @@ dl_toolbox: "torch" # The deep learning toolbox. Choices: "torch", "mindspore", "tensorlayer" -project_name: "XuanPolicy_Benchmark" +project_name: "XuanCe_Benchmark" logger: "tensorboard" # Choices: tensorboard, wandb. wandb_user_name: "papers_liu" diff --git a/xuanpolicy/configs/c51/atari.yaml b/xuance/configs/c51/atari.yaml similarity index 100% rename from xuanpolicy/configs/c51/atari.yaml rename to xuance/configs/c51/atari.yaml diff --git a/xuanpolicy/configs/c51/box2d/CarRacing-v2.yaml b/xuance/configs/c51/box2d/CarRacing-v2.yaml similarity index 100% rename from xuanpolicy/configs/c51/box2d/CarRacing-v2.yaml rename to xuance/configs/c51/box2d/CarRacing-v2.yaml diff --git a/xuanpolicy/configs/c51/box2d/LunarLander-v2.yaml b/xuance/configs/c51/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/c51/box2d/LunarLander-v2.yaml rename to xuance/configs/c51/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/c51/classic_control/Acrobot-v1.yaml b/xuance/configs/c51/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/c51/classic_control/Acrobot-v1.yaml rename to xuance/configs/c51/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/c51/classic_control/CartPole-v1.yaml b/xuance/configs/c51/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/c51/classic_control/CartPole-v1.yaml rename to xuance/configs/c51/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/c51/classic_control/MountainCar-v0.yaml b/xuance/configs/c51/classic_control/MountainCar-v0.yaml similarity index 100% rename from xuanpolicy/configs/c51/classic_control/MountainCar-v0.yaml rename to xuance/configs/c51/classic_control/MountainCar-v0.yaml diff --git a/xuanpolicy/configs/coma/mpe/simple_spread_v3.yaml b/xuance/configs/coma/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/coma/mpe/simple_spread_v3.yaml rename to xuance/configs/coma/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/coma/sc2/25m.yaml b/xuance/configs/coma/sc2/25m.yaml similarity index 100% rename from xuanpolicy/configs/coma/sc2/25m.yaml rename to xuance/configs/coma/sc2/25m.yaml diff --git a/xuanpolicy/configs/coma/sc2/2m_vs_1z.yaml b/xuance/configs/coma/sc2/2m_vs_1z.yaml similarity index 100% rename from xuanpolicy/configs/coma/sc2/2m_vs_1z.yaml rename to xuance/configs/coma/sc2/2m_vs_1z.yaml diff --git a/xuanpolicy/configs/coma/sc2/3m.yaml b/xuance/configs/coma/sc2/3m.yaml similarity index 100% rename from xuanpolicy/configs/coma/sc2/3m.yaml rename to xuance/configs/coma/sc2/3m.yaml diff --git a/xuanpolicy/configs/coma/sc2/5m_vs_6m.yaml b/xuance/configs/coma/sc2/5m_vs_6m.yaml similarity index 100% rename from xuanpolicy/configs/coma/sc2/5m_vs_6m.yaml rename to xuance/configs/coma/sc2/5m_vs_6m.yaml diff --git a/xuanpolicy/configs/coma/sc2/8m.yaml b/xuance/configs/coma/sc2/8m.yaml similarity index 100% rename from xuanpolicy/configs/coma/sc2/8m.yaml rename to xuance/configs/coma/sc2/8m.yaml diff --git a/xuanpolicy/configs/coma/sc2/8m_vs_9m.yaml b/xuance/configs/coma/sc2/8m_vs_9m.yaml similarity index 100% rename from xuanpolicy/configs/coma/sc2/8m_vs_9m.yaml rename to xuance/configs/coma/sc2/8m_vs_9m.yaml diff --git a/xuanpolicy/configs/coma/sc2/MMM2.yaml b/xuance/configs/coma/sc2/MMM2.yaml similarity index 100% rename from xuanpolicy/configs/coma/sc2/MMM2.yaml rename to xuance/configs/coma/sc2/MMM2.yaml diff --git a/xuanpolicy/configs/coma/sc2/corridor.yaml b/xuance/configs/coma/sc2/corridor.yaml similarity index 100% rename from xuanpolicy/configs/coma/sc2/corridor.yaml rename to xuance/configs/coma/sc2/corridor.yaml diff --git a/xuanpolicy/configs/dcg/mpe/simple_spread_v3.yaml b/xuance/configs/dcg/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/dcg/mpe/simple_spread_v3.yaml rename to xuance/configs/dcg/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/dcg/sc2/25m.yaml b/xuance/configs/dcg/sc2/25m.yaml similarity index 100% rename from xuanpolicy/configs/dcg/sc2/25m.yaml rename to xuance/configs/dcg/sc2/25m.yaml diff --git a/xuanpolicy/configs/dcg/sc2/2m_vs_1z.yaml b/xuance/configs/dcg/sc2/2m_vs_1z.yaml similarity index 100% rename from xuanpolicy/configs/dcg/sc2/2m_vs_1z.yaml rename to xuance/configs/dcg/sc2/2m_vs_1z.yaml diff --git a/xuanpolicy/configs/dcg/sc2/3m.yaml b/xuance/configs/dcg/sc2/3m.yaml similarity index 100% rename from xuanpolicy/configs/dcg/sc2/3m.yaml rename to xuance/configs/dcg/sc2/3m.yaml diff --git a/xuanpolicy/configs/dcg/sc2/5m_vs_6m.yaml b/xuance/configs/dcg/sc2/5m_vs_6m.yaml similarity index 100% rename from xuanpolicy/configs/dcg/sc2/5m_vs_6m.yaml rename to xuance/configs/dcg/sc2/5m_vs_6m.yaml diff --git a/xuanpolicy/configs/dcg/sc2/8m.yaml b/xuance/configs/dcg/sc2/8m.yaml similarity index 100% rename from xuanpolicy/configs/dcg/sc2/8m.yaml rename to xuance/configs/dcg/sc2/8m.yaml diff --git a/xuanpolicy/configs/dcg/sc2/8m_vs_9m.yaml b/xuance/configs/dcg/sc2/8m_vs_9m.yaml similarity index 100% rename from xuanpolicy/configs/dcg/sc2/8m_vs_9m.yaml rename to xuance/configs/dcg/sc2/8m_vs_9m.yaml diff --git a/xuanpolicy/configs/dcg/sc2/MMM2.yaml b/xuance/configs/dcg/sc2/MMM2.yaml similarity index 100% rename from xuanpolicy/configs/dcg/sc2/MMM2.yaml rename to xuance/configs/dcg/sc2/MMM2.yaml diff --git a/xuanpolicy/configs/dcg/sc2/corridor.yaml b/xuance/configs/dcg/sc2/corridor.yaml similarity index 100% rename from xuanpolicy/configs/dcg/sc2/corridor.yaml rename to xuance/configs/dcg/sc2/corridor.yaml diff --git a/xuanpolicy/configs/ddpg/box2d/BipedalWalker-v3.yaml b/xuance/configs/ddpg/box2d/BipedalWalker-v3.yaml similarity index 100% rename from xuanpolicy/configs/ddpg/box2d/BipedalWalker-v3.yaml rename to xuance/configs/ddpg/box2d/BipedalWalker-v3.yaml diff --git a/xuanpolicy/configs/ddpg/classic_control/Pendulum-v1.yaml b/xuance/configs/ddpg/classic_control/Pendulum-v1.yaml similarity index 100% rename from xuanpolicy/configs/ddpg/classic_control/Pendulum-v1.yaml rename to xuance/configs/ddpg/classic_control/Pendulum-v1.yaml diff --git a/xuanpolicy/configs/ddpg/mujoco.yaml b/xuance/configs/ddpg/mujoco.yaml similarity index 100% rename from xuanpolicy/configs/ddpg/mujoco.yaml rename to xuance/configs/ddpg/mujoco.yaml diff --git a/xuanpolicy/configs/ddqn/atari.yaml b/xuance/configs/ddqn/atari.yaml similarity index 100% rename from xuanpolicy/configs/ddqn/atari.yaml rename to xuance/configs/ddqn/atari.yaml diff --git a/xuanpolicy/configs/ddqn/box2d/CarRacing-v2.yaml b/xuance/configs/ddqn/box2d/CarRacing-v2.yaml similarity index 100% rename from xuanpolicy/configs/ddqn/box2d/CarRacing-v2.yaml rename to xuance/configs/ddqn/box2d/CarRacing-v2.yaml diff --git a/xuanpolicy/configs/ddqn/box2d/LunarLander-v2.yaml b/xuance/configs/ddqn/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/ddqn/box2d/LunarLander-v2.yaml rename to xuance/configs/ddqn/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/ddqn/classic_control/Acrobot-v1.yaml b/xuance/configs/ddqn/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/ddqn/classic_control/Acrobot-v1.yaml rename to xuance/configs/ddqn/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/ddqn/classic_control/CartPole-v1.yaml b/xuance/configs/ddqn/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/ddqn/classic_control/CartPole-v1.yaml rename to xuance/configs/ddqn/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/ddqn/classic_control/MountainCar-v0.yaml b/xuance/configs/ddqn/classic_control/MountainCar-v0.yaml similarity index 100% rename from xuanpolicy/configs/ddqn/classic_control/MountainCar-v0.yaml rename to xuance/configs/ddqn/classic_control/MountainCar-v0.yaml diff --git a/xuanpolicy/configs/dqn/atari.yaml b/xuance/configs/dqn/atari.yaml similarity index 100% rename from xuanpolicy/configs/dqn/atari.yaml rename to xuance/configs/dqn/atari.yaml diff --git a/xuanpolicy/configs/dqn/box2d/CarRacing-v2.yaml b/xuance/configs/dqn/box2d/CarRacing-v2.yaml similarity index 100% rename from xuanpolicy/configs/dqn/box2d/CarRacing-v2.yaml rename to xuance/configs/dqn/box2d/CarRacing-v2.yaml diff --git a/xuanpolicy/configs/dqn/box2d/LunarLander-v2.yaml b/xuance/configs/dqn/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/dqn/box2d/LunarLander-v2.yaml rename to xuance/configs/dqn/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/dqn/classic_control/Acrobot-v1.yaml b/xuance/configs/dqn/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/dqn/classic_control/Acrobot-v1.yaml rename to xuance/configs/dqn/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/dqn/classic_control/CartPole-v1.yaml b/xuance/configs/dqn/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/dqn/classic_control/CartPole-v1.yaml rename to xuance/configs/dqn/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/dqn/classic_control/MountainCar-v0.yaml b/xuance/configs/dqn/classic_control/MountainCar-v0.yaml similarity index 100% rename from xuanpolicy/configs/dqn/classic_control/MountainCar-v0.yaml rename to xuance/configs/dqn/classic_control/MountainCar-v0.yaml diff --git a/xuanpolicy/configs/drqn/atari.yaml b/xuance/configs/drqn/atari.yaml similarity index 100% rename from xuanpolicy/configs/drqn/atari.yaml rename to xuance/configs/drqn/atari.yaml diff --git a/xuanpolicy/configs/drqn/box2d/CarRacing-v2.yaml b/xuance/configs/drqn/box2d/CarRacing-v2.yaml similarity index 100% rename from xuanpolicy/configs/drqn/box2d/CarRacing-v2.yaml rename to xuance/configs/drqn/box2d/CarRacing-v2.yaml diff --git a/xuanpolicy/configs/drqn/box2d/LunarLander-v2.yaml b/xuance/configs/drqn/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/drqn/box2d/LunarLander-v2.yaml rename to xuance/configs/drqn/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/drqn/classic_control/Acrobot-v1.yaml b/xuance/configs/drqn/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/drqn/classic_control/Acrobot-v1.yaml rename to xuance/configs/drqn/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/drqn/classic_control/CartPole-v1.yaml b/xuance/configs/drqn/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/drqn/classic_control/CartPole-v1.yaml rename to xuance/configs/drqn/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/drqn/classic_control/MountainCar-v0.yaml b/xuance/configs/drqn/classic_control/MountainCar-v0.yaml similarity index 100% rename from xuanpolicy/configs/drqn/classic_control/MountainCar-v0.yaml rename to xuance/configs/drqn/classic_control/MountainCar-v0.yaml diff --git a/xuanpolicy/configs/dueldqn/atari.yaml b/xuance/configs/dueldqn/atari.yaml similarity index 100% rename from xuanpolicy/configs/dueldqn/atari.yaml rename to xuance/configs/dueldqn/atari.yaml diff --git a/xuanpolicy/configs/dueldqn/box2d/CarRacing-v2.yaml b/xuance/configs/dueldqn/box2d/CarRacing-v2.yaml similarity index 100% rename from xuanpolicy/configs/dueldqn/box2d/CarRacing-v2.yaml rename to xuance/configs/dueldqn/box2d/CarRacing-v2.yaml diff --git a/xuanpolicy/configs/dueldqn/box2d/LunarLander-v2.yaml b/xuance/configs/dueldqn/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/dueldqn/box2d/LunarLander-v2.yaml rename to xuance/configs/dueldqn/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/dueldqn/classic_control/Acrobot-v1.yaml b/xuance/configs/dueldqn/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/dueldqn/classic_control/Acrobot-v1.yaml rename to xuance/configs/dueldqn/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/dueldqn/classic_control/CartPole-v1.yaml b/xuance/configs/dueldqn/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/dueldqn/classic_control/CartPole-v1.yaml rename to xuance/configs/dueldqn/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/dueldqn/classic_control/MountainCar-v0.yaml b/xuance/configs/dueldqn/classic_control/MountainCar-v0.yaml similarity index 100% rename from xuanpolicy/configs/dueldqn/classic_control/MountainCar-v0.yaml rename to xuance/configs/dueldqn/classic_control/MountainCar-v0.yaml diff --git a/xuanpolicy/configs/iddpg/mpe/simple_adversary_v3.yaml b/xuance/configs/iddpg/mpe/simple_adversary_v3.yaml similarity index 100% rename from xuanpolicy/configs/iddpg/mpe/simple_adversary_v3.yaml rename to xuance/configs/iddpg/mpe/simple_adversary_v3.yaml diff --git a/xuanpolicy/configs/iddpg/mpe/simple_push_v3.yaml b/xuance/configs/iddpg/mpe/simple_push_v3.yaml similarity index 100% rename from xuanpolicy/configs/iddpg/mpe/simple_push_v3.yaml rename to xuance/configs/iddpg/mpe/simple_push_v3.yaml diff --git a/xuanpolicy/configs/iddpg/mpe/simple_spread_v3.yaml b/xuance/configs/iddpg/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/iddpg/mpe/simple_spread_v3.yaml rename to xuance/configs/iddpg/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/ippo/mpe/simple_spread_v3.yaml b/xuance/configs/ippo/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/ippo/mpe/simple_spread_v3.yaml rename to xuance/configs/ippo/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/ippo/sc2/25m.yaml b/xuance/configs/ippo/sc2/25m.yaml similarity index 100% rename from xuanpolicy/configs/ippo/sc2/25m.yaml rename to xuance/configs/ippo/sc2/25m.yaml diff --git a/xuanpolicy/configs/ippo/sc2/2m_vs_1z.yaml b/xuance/configs/ippo/sc2/2m_vs_1z.yaml similarity index 100% rename from xuanpolicy/configs/ippo/sc2/2m_vs_1z.yaml rename to xuance/configs/ippo/sc2/2m_vs_1z.yaml diff --git a/xuanpolicy/configs/ippo/sc2/3m.yaml b/xuance/configs/ippo/sc2/3m.yaml similarity index 100% rename from xuanpolicy/configs/ippo/sc2/3m.yaml rename to xuance/configs/ippo/sc2/3m.yaml diff --git a/xuanpolicy/configs/ippo/sc2/5m_vs_6m.yaml b/xuance/configs/ippo/sc2/5m_vs_6m.yaml similarity index 100% rename from xuanpolicy/configs/ippo/sc2/5m_vs_6m.yaml rename to xuance/configs/ippo/sc2/5m_vs_6m.yaml diff --git a/xuanpolicy/configs/ippo/sc2/8m.yaml b/xuance/configs/ippo/sc2/8m.yaml similarity index 100% rename from xuanpolicy/configs/ippo/sc2/8m.yaml rename to xuance/configs/ippo/sc2/8m.yaml diff --git a/xuanpolicy/configs/ippo/sc2/8m_vs_9m.yaml b/xuance/configs/ippo/sc2/8m_vs_9m.yaml similarity index 100% rename from xuanpolicy/configs/ippo/sc2/8m_vs_9m.yaml rename to xuance/configs/ippo/sc2/8m_vs_9m.yaml diff --git a/xuanpolicy/configs/ippo/sc2/MMM2.yaml b/xuance/configs/ippo/sc2/MMM2.yaml similarity index 100% rename from xuanpolicy/configs/ippo/sc2/MMM2.yaml rename to xuance/configs/ippo/sc2/MMM2.yaml diff --git a/xuanpolicy/configs/ippo/sc2/corridor.yaml b/xuance/configs/ippo/sc2/corridor.yaml similarity index 100% rename from xuanpolicy/configs/ippo/sc2/corridor.yaml rename to xuance/configs/ippo/sc2/corridor.yaml diff --git a/xuanpolicy/configs/iql/football/3v1.yaml b/xuance/configs/iql/football/3v1.yaml similarity index 100% rename from xuanpolicy/configs/iql/football/3v1.yaml rename to xuance/configs/iql/football/3v1.yaml diff --git a/xuanpolicy/configs/iql/magent2/adversarial_pursuit_v4.yaml b/xuance/configs/iql/magent2/adversarial_pursuit_v4.yaml similarity index 100% rename from xuanpolicy/configs/iql/magent2/adversarial_pursuit_v4.yaml rename to xuance/configs/iql/magent2/adversarial_pursuit_v4.yaml diff --git a/xuanpolicy/configs/iql/mpe/simple_spread_v3.yaml b/xuance/configs/iql/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/iql/mpe/simple_spread_v3.yaml rename to xuance/configs/iql/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/iql/sc2/25m.yaml b/xuance/configs/iql/sc2/25m.yaml similarity index 100% rename from xuanpolicy/configs/iql/sc2/25m.yaml rename to xuance/configs/iql/sc2/25m.yaml diff --git a/xuanpolicy/configs/iql/sc2/2m_vs_1z.yaml b/xuance/configs/iql/sc2/2m_vs_1z.yaml similarity index 100% rename from xuanpolicy/configs/iql/sc2/2m_vs_1z.yaml rename to xuance/configs/iql/sc2/2m_vs_1z.yaml diff --git a/xuanpolicy/configs/iql/sc2/3m.yaml b/xuance/configs/iql/sc2/3m.yaml similarity index 100% rename from xuanpolicy/configs/iql/sc2/3m.yaml rename to xuance/configs/iql/sc2/3m.yaml diff --git a/xuanpolicy/configs/iql/sc2/5m_vs_6m.yaml b/xuance/configs/iql/sc2/5m_vs_6m.yaml similarity index 100% rename from xuanpolicy/configs/iql/sc2/5m_vs_6m.yaml rename to xuance/configs/iql/sc2/5m_vs_6m.yaml diff --git a/xuanpolicy/configs/iql/sc2/8m.yaml b/xuance/configs/iql/sc2/8m.yaml similarity index 100% rename from xuanpolicy/configs/iql/sc2/8m.yaml rename to xuance/configs/iql/sc2/8m.yaml diff --git a/xuanpolicy/configs/iql/sc2/8m_vs_9m.yaml b/xuance/configs/iql/sc2/8m_vs_9m.yaml similarity index 100% rename from xuanpolicy/configs/iql/sc2/8m_vs_9m.yaml rename to xuance/configs/iql/sc2/8m_vs_9m.yaml diff --git a/xuanpolicy/configs/iql/sc2/MMM2.yaml b/xuance/configs/iql/sc2/MMM2.yaml similarity index 100% rename from xuanpolicy/configs/iql/sc2/MMM2.yaml rename to xuance/configs/iql/sc2/MMM2.yaml diff --git a/xuanpolicy/configs/iql/sc2/corridor.yaml b/xuance/configs/iql/sc2/corridor.yaml similarity index 100% rename from xuanpolicy/configs/iql/sc2/corridor.yaml rename to xuance/configs/iql/sc2/corridor.yaml diff --git a/xuanpolicy/configs/isac/mpe/simple_adversary_v3.yaml b/xuance/configs/isac/mpe/simple_adversary_v3.yaml similarity index 100% rename from xuanpolicy/configs/isac/mpe/simple_adversary_v3.yaml rename to xuance/configs/isac/mpe/simple_adversary_v3.yaml diff --git a/xuanpolicy/configs/isac/mpe/simple_push_v3.yaml b/xuance/configs/isac/mpe/simple_push_v3.yaml similarity index 100% rename from xuanpolicy/configs/isac/mpe/simple_push_v3.yaml rename to xuance/configs/isac/mpe/simple_push_v3.yaml diff --git a/xuanpolicy/configs/isac/mpe/simple_spread_v3.yaml b/xuance/configs/isac/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/isac/mpe/simple_spread_v3.yaml rename to xuance/configs/isac/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/maddpg/mpe/simple_adversary_v3.yaml b/xuance/configs/maddpg/mpe/simple_adversary_v3.yaml similarity index 100% rename from xuanpolicy/configs/maddpg/mpe/simple_adversary_v3.yaml rename to xuance/configs/maddpg/mpe/simple_adversary_v3.yaml diff --git a/xuanpolicy/configs/maddpg/mpe/simple_push_v3.yaml b/xuance/configs/maddpg/mpe/simple_push_v3.yaml similarity index 100% rename from xuanpolicy/configs/maddpg/mpe/simple_push_v3.yaml rename to xuance/configs/maddpg/mpe/simple_push_v3.yaml diff --git a/xuanpolicy/configs/maddpg/mpe/simple_spread_v3.yaml b/xuance/configs/maddpg/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/maddpg/mpe/simple_spread_v3.yaml rename to xuance/configs/maddpg/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/mappo/mpe/simple_spread_v3.yaml b/xuance/configs/mappo/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/mappo/mpe/simple_spread_v3.yaml rename to xuance/configs/mappo/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/mappo/sc2/25m.yaml b/xuance/configs/mappo/sc2/25m.yaml similarity index 100% rename from xuanpolicy/configs/mappo/sc2/25m.yaml rename to xuance/configs/mappo/sc2/25m.yaml diff --git a/xuanpolicy/configs/mappo/sc2/2m_vs_1z.yaml b/xuance/configs/mappo/sc2/2m_vs_1z.yaml similarity index 100% rename from xuanpolicy/configs/mappo/sc2/2m_vs_1z.yaml rename to xuance/configs/mappo/sc2/2m_vs_1z.yaml diff --git a/xuanpolicy/configs/mappo/sc2/3m.yaml b/xuance/configs/mappo/sc2/3m.yaml similarity index 100% rename from xuanpolicy/configs/mappo/sc2/3m.yaml rename to xuance/configs/mappo/sc2/3m.yaml diff --git a/xuanpolicy/configs/mappo/sc2/5m_vs_6m.yaml b/xuance/configs/mappo/sc2/5m_vs_6m.yaml similarity index 100% rename from xuanpolicy/configs/mappo/sc2/5m_vs_6m.yaml rename to xuance/configs/mappo/sc2/5m_vs_6m.yaml diff --git a/xuanpolicy/configs/mappo/sc2/8m.yaml b/xuance/configs/mappo/sc2/8m.yaml similarity index 100% rename from xuanpolicy/configs/mappo/sc2/8m.yaml rename to xuance/configs/mappo/sc2/8m.yaml diff --git a/xuanpolicy/configs/mappo/sc2/8m_vs_9m.yaml b/xuance/configs/mappo/sc2/8m_vs_9m.yaml similarity index 100% rename from xuanpolicy/configs/mappo/sc2/8m_vs_9m.yaml rename to xuance/configs/mappo/sc2/8m_vs_9m.yaml diff --git a/xuanpolicy/configs/mappo/sc2/MMM2.yaml b/xuance/configs/mappo/sc2/MMM2.yaml similarity index 100% rename from xuanpolicy/configs/mappo/sc2/MMM2.yaml rename to xuance/configs/mappo/sc2/MMM2.yaml diff --git a/xuanpolicy/configs/mappo/sc2/corridor.yaml b/xuance/configs/mappo/sc2/corridor.yaml similarity index 100% rename from xuanpolicy/configs/mappo/sc2/corridor.yaml rename to xuance/configs/mappo/sc2/corridor.yaml diff --git a/xuanpolicy/configs/masac/mpe/simple_adversary_v3.yaml b/xuance/configs/masac/mpe/simple_adversary_v3.yaml similarity index 100% rename from xuanpolicy/configs/masac/mpe/simple_adversary_v3.yaml rename to xuance/configs/masac/mpe/simple_adversary_v3.yaml diff --git a/xuanpolicy/configs/masac/mpe/simple_push_v3.yaml b/xuance/configs/masac/mpe/simple_push_v3.yaml similarity index 100% rename from xuanpolicy/configs/masac/mpe/simple_push_v3.yaml rename to xuance/configs/masac/mpe/simple_push_v3.yaml diff --git a/xuanpolicy/configs/masac/mpe/simple_spread_v3.yaml b/xuance/configs/masac/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/masac/mpe/simple_spread_v3.yaml rename to xuance/configs/masac/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/matd3/mpe/simple_adversary_v3.yaml b/xuance/configs/matd3/mpe/simple_adversary_v3.yaml similarity index 100% rename from xuanpolicy/configs/matd3/mpe/simple_adversary_v3.yaml rename to xuance/configs/matd3/mpe/simple_adversary_v3.yaml diff --git a/xuanpolicy/configs/matd3/mpe/simple_push_v3.yaml b/xuance/configs/matd3/mpe/simple_push_v3.yaml similarity index 100% rename from xuanpolicy/configs/matd3/mpe/simple_push_v3.yaml rename to xuance/configs/matd3/mpe/simple_push_v3.yaml diff --git a/xuanpolicy/configs/matd3/mpe/simple_spread_v3.yaml b/xuance/configs/matd3/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/matd3/mpe/simple_spread_v3.yaml rename to xuance/configs/matd3/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/mfac/mpe/simple_spread_v3.yaml b/xuance/configs/mfac/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/mfac/mpe/simple_spread_v3.yaml rename to xuance/configs/mfac/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/mfq/magent2/adversarial_pursuit_v4.yaml b/xuance/configs/mfq/magent2/adversarial_pursuit_v4.yaml similarity index 100% rename from xuanpolicy/configs/mfq/magent2/adversarial_pursuit_v4.yaml rename to xuance/configs/mfq/magent2/adversarial_pursuit_v4.yaml diff --git a/xuanpolicy/configs/mfq/mpe/simple_spread_v3.yaml b/xuance/configs/mfq/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/mfq/mpe/simple_spread_v3.yaml rename to xuance/configs/mfq/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/mpdqn/Platform.yaml b/xuance/configs/mpdqn/Platform.yaml similarity index 100% rename from xuanpolicy/configs/mpdqn/Platform.yaml rename to xuance/configs/mpdqn/Platform.yaml diff --git a/xuanpolicy/configs/noisydqn/atari.yaml b/xuance/configs/noisydqn/atari.yaml similarity index 100% rename from xuanpolicy/configs/noisydqn/atari.yaml rename to xuance/configs/noisydqn/atari.yaml diff --git a/xuanpolicy/configs/noisydqn/box2d/CarRacing-v2.yaml b/xuance/configs/noisydqn/box2d/CarRacing-v2.yaml similarity index 100% rename from xuanpolicy/configs/noisydqn/box2d/CarRacing-v2.yaml rename to xuance/configs/noisydqn/box2d/CarRacing-v2.yaml diff --git a/xuanpolicy/configs/noisydqn/box2d/LunarLander-v2.yaml b/xuance/configs/noisydqn/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/noisydqn/box2d/LunarLander-v2.yaml rename to xuance/configs/noisydqn/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/noisydqn/classic_control/Acrobot-v1.yaml b/xuance/configs/noisydqn/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/noisydqn/classic_control/Acrobot-v1.yaml rename to xuance/configs/noisydqn/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/noisydqn/classic_control/CartPole-v1.yaml b/xuance/configs/noisydqn/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/noisydqn/classic_control/CartPole-v1.yaml rename to xuance/configs/noisydqn/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/noisydqn/classic_control/MountainCar-v0.yaml b/xuance/configs/noisydqn/classic_control/MountainCar-v0.yaml similarity index 100% rename from xuanpolicy/configs/noisydqn/classic_control/MountainCar-v0.yaml rename to xuance/configs/noisydqn/classic_control/MountainCar-v0.yaml diff --git a/xuanpolicy/configs/pdqn/Platform.yaml b/xuance/configs/pdqn/Platform.yaml similarity index 100% rename from xuanpolicy/configs/pdqn/Platform.yaml rename to xuance/configs/pdqn/Platform.yaml diff --git a/xuanpolicy/configs/perdqn/atari.yaml b/xuance/configs/perdqn/atari.yaml similarity index 100% rename from xuanpolicy/configs/perdqn/atari.yaml rename to xuance/configs/perdqn/atari.yaml diff --git a/xuanpolicy/configs/perdqn/box2d/CarRacing-v2.yaml b/xuance/configs/perdqn/box2d/CarRacing-v2.yaml similarity index 100% rename from xuanpolicy/configs/perdqn/box2d/CarRacing-v2.yaml rename to xuance/configs/perdqn/box2d/CarRacing-v2.yaml diff --git a/xuanpolicy/configs/perdqn/box2d/LunarLander-v2.yaml b/xuance/configs/perdqn/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/perdqn/box2d/LunarLander-v2.yaml rename to xuance/configs/perdqn/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/perdqn/classic_control/Acrobot-v1.yaml b/xuance/configs/perdqn/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/perdqn/classic_control/Acrobot-v1.yaml rename to xuance/configs/perdqn/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/perdqn/classic_control/CartPole-v1.yaml b/xuance/configs/perdqn/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/perdqn/classic_control/CartPole-v1.yaml rename to xuance/configs/perdqn/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/perdqn/classic_control/MountainCar-v1.yaml b/xuance/configs/perdqn/classic_control/MountainCar-v1.yaml similarity index 100% rename from xuanpolicy/configs/perdqn/classic_control/MountainCar-v1.yaml rename to xuance/configs/perdqn/classic_control/MountainCar-v1.yaml diff --git a/xuanpolicy/configs/pg/box2d/BipedalWalker-v3.yaml b/xuance/configs/pg/box2d/BipedalWalker-v3.yaml similarity index 100% rename from xuanpolicy/configs/pg/box2d/BipedalWalker-v3.yaml rename to xuance/configs/pg/box2d/BipedalWalker-v3.yaml diff --git a/xuanpolicy/configs/pg/box2d/LunarLander-v2.yaml b/xuance/configs/pg/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/pg/box2d/LunarLander-v2.yaml rename to xuance/configs/pg/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/pg/classic_control/Acrobot-v1.yaml b/xuance/configs/pg/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/pg/classic_control/Acrobot-v1.yaml rename to xuance/configs/pg/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/pg/classic_control/CartPole-v1.yaml b/xuance/configs/pg/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/pg/classic_control/CartPole-v1.yaml rename to xuance/configs/pg/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/pg/classic_control/MountainCar-v0.yaml b/xuance/configs/pg/classic_control/MountainCar-v0.yaml similarity index 100% rename from xuanpolicy/configs/pg/classic_control/MountainCar-v0.yaml rename to xuance/configs/pg/classic_control/MountainCar-v0.yaml diff --git a/xuanpolicy/configs/pg/classic_control/Pendulum-v1.yaml b/xuance/configs/pg/classic_control/Pendulum-v1.yaml similarity index 100% rename from xuanpolicy/configs/pg/classic_control/Pendulum-v1.yaml rename to xuance/configs/pg/classic_control/Pendulum-v1.yaml diff --git a/xuanpolicy/configs/pg/mujoco.yaml b/xuance/configs/pg/mujoco.yaml similarity index 100% rename from xuanpolicy/configs/pg/mujoco.yaml rename to xuance/configs/pg/mujoco.yaml diff --git a/xuanpolicy/configs/ppg/box2d/BipedalWalker-v3.yaml b/xuance/configs/ppg/box2d/BipedalWalker-v3.yaml similarity index 100% rename from xuanpolicy/configs/ppg/box2d/BipedalWalker-v3.yaml rename to xuance/configs/ppg/box2d/BipedalWalker-v3.yaml diff --git a/xuanpolicy/configs/ppg/box2d/LunarLander-v2.yaml b/xuance/configs/ppg/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/ppg/box2d/LunarLander-v2.yaml rename to xuance/configs/ppg/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/ppg/classic_control/Acrobot-v1.yaml b/xuance/configs/ppg/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/ppg/classic_control/Acrobot-v1.yaml rename to xuance/configs/ppg/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/ppg/classic_control/CartPole-v1.yaml b/xuance/configs/ppg/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/ppg/classic_control/CartPole-v1.yaml rename to xuance/configs/ppg/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/ppg/classic_control/MountainCar-v0.yaml b/xuance/configs/ppg/classic_control/MountainCar-v0.yaml similarity index 100% rename from xuanpolicy/configs/ppg/classic_control/MountainCar-v0.yaml rename to xuance/configs/ppg/classic_control/MountainCar-v0.yaml diff --git a/xuanpolicy/configs/ppg/classic_control/Pendulum-v1.yaml b/xuance/configs/ppg/classic_control/Pendulum-v1.yaml similarity index 100% rename from xuanpolicy/configs/ppg/classic_control/Pendulum-v1.yaml rename to xuance/configs/ppg/classic_control/Pendulum-v1.yaml diff --git a/xuanpolicy/configs/ppg/mujoco.yaml b/xuance/configs/ppg/mujoco.yaml similarity index 100% rename from xuanpolicy/configs/ppg/mujoco.yaml rename to xuance/configs/ppg/mujoco.yaml diff --git a/xuanpolicy/configs/ppo/atari.yaml b/xuance/configs/ppo/atari.yaml similarity index 100% rename from xuanpolicy/configs/ppo/atari.yaml rename to xuance/configs/ppo/atari.yaml diff --git a/xuanpolicy/configs/ppo/box2d/BipedalWalker-v3.yaml b/xuance/configs/ppo/box2d/BipedalWalker-v3.yaml similarity index 100% rename from xuanpolicy/configs/ppo/box2d/BipedalWalker-v3.yaml rename to xuance/configs/ppo/box2d/BipedalWalker-v3.yaml diff --git a/xuanpolicy/configs/ppo/box2d/CarRacing-v2.yaml b/xuance/configs/ppo/box2d/CarRacing-v2.yaml similarity index 100% rename from xuanpolicy/configs/ppo/box2d/CarRacing-v2.yaml rename to xuance/configs/ppo/box2d/CarRacing-v2.yaml diff --git a/xuanpolicy/configs/ppo/box2d/LunarLander-v2.yaml b/xuance/configs/ppo/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/ppo/box2d/LunarLander-v2.yaml rename to xuance/configs/ppo/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/ppo/classic_control/Acrobot-v1.yaml b/xuance/configs/ppo/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/ppo/classic_control/Acrobot-v1.yaml rename to xuance/configs/ppo/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/ppo/classic_control/CartPole-v1.yaml b/xuance/configs/ppo/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/ppo/classic_control/CartPole-v1.yaml rename to xuance/configs/ppo/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/ppo/classic_control/MountainCar-v0.yaml b/xuance/configs/ppo/classic_control/MountainCar-v0.yaml similarity index 100% rename from xuanpolicy/configs/ppo/classic_control/MountainCar-v0.yaml rename to xuance/configs/ppo/classic_control/MountainCar-v0.yaml diff --git a/xuanpolicy/configs/ppo/classic_control/Pendulum-v1.yaml b/xuance/configs/ppo/classic_control/Pendulum-v1.yaml similarity index 100% rename from xuanpolicy/configs/ppo/classic_control/Pendulum-v1.yaml rename to xuance/configs/ppo/classic_control/Pendulum-v1.yaml diff --git a/xuanpolicy/configs/ppo/mujoco.yaml b/xuance/configs/ppo/mujoco.yaml similarity index 100% rename from xuanpolicy/configs/ppo/mujoco.yaml rename to xuance/configs/ppo/mujoco.yaml diff --git a/xuanpolicy/configs/qmix/mpe/simple_spread_v3.yaml b/xuance/configs/qmix/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/qmix/mpe/simple_spread_v3.yaml rename to xuance/configs/qmix/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/qmix/sc2/25m.yaml b/xuance/configs/qmix/sc2/25m.yaml similarity index 100% rename from xuanpolicy/configs/qmix/sc2/25m.yaml rename to xuance/configs/qmix/sc2/25m.yaml diff --git a/xuanpolicy/configs/qmix/sc2/2m_vs_1z.yaml b/xuance/configs/qmix/sc2/2m_vs_1z.yaml similarity index 100% rename from xuanpolicy/configs/qmix/sc2/2m_vs_1z.yaml rename to xuance/configs/qmix/sc2/2m_vs_1z.yaml diff --git a/xuanpolicy/configs/qmix/sc2/3m.yaml b/xuance/configs/qmix/sc2/3m.yaml similarity index 100% rename from xuanpolicy/configs/qmix/sc2/3m.yaml rename to xuance/configs/qmix/sc2/3m.yaml diff --git a/xuanpolicy/configs/qmix/sc2/5m_vs_6m.yaml b/xuance/configs/qmix/sc2/5m_vs_6m.yaml similarity index 100% rename from xuanpolicy/configs/qmix/sc2/5m_vs_6m.yaml rename to xuance/configs/qmix/sc2/5m_vs_6m.yaml diff --git a/xuanpolicy/configs/qmix/sc2/8m.yaml b/xuance/configs/qmix/sc2/8m.yaml similarity index 100% rename from xuanpolicy/configs/qmix/sc2/8m.yaml rename to xuance/configs/qmix/sc2/8m.yaml diff --git a/xuanpolicy/configs/qmix/sc2/8m_vs_9m.yaml b/xuance/configs/qmix/sc2/8m_vs_9m.yaml similarity index 100% rename from xuanpolicy/configs/qmix/sc2/8m_vs_9m.yaml rename to xuance/configs/qmix/sc2/8m_vs_9m.yaml diff --git a/xuanpolicy/configs/qmix/sc2/MMM2.yaml b/xuance/configs/qmix/sc2/MMM2.yaml similarity index 100% rename from xuanpolicy/configs/qmix/sc2/MMM2.yaml rename to xuance/configs/qmix/sc2/MMM2.yaml diff --git a/xuanpolicy/configs/qmix/sc2/corridor.yaml b/xuance/configs/qmix/sc2/corridor.yaml similarity index 100% rename from xuanpolicy/configs/qmix/sc2/corridor.yaml rename to xuance/configs/qmix/sc2/corridor.yaml diff --git a/xuanpolicy/configs/qrdqn/atari.yaml b/xuance/configs/qrdqn/atari.yaml similarity index 100% rename from xuanpolicy/configs/qrdqn/atari.yaml rename to xuance/configs/qrdqn/atari.yaml diff --git a/xuanpolicy/configs/qrdqn/box2d/CarRacing-v2.yaml b/xuance/configs/qrdqn/box2d/CarRacing-v2.yaml similarity index 100% rename from xuanpolicy/configs/qrdqn/box2d/CarRacing-v2.yaml rename to xuance/configs/qrdqn/box2d/CarRacing-v2.yaml diff --git a/xuanpolicy/configs/qrdqn/box2d/LunarLander-v2.yaml b/xuance/configs/qrdqn/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/qrdqn/box2d/LunarLander-v2.yaml rename to xuance/configs/qrdqn/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/qrdqn/classic_control/Acrobot-v1.yaml b/xuance/configs/qrdqn/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/qrdqn/classic_control/Acrobot-v1.yaml rename to xuance/configs/qrdqn/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/qrdqn/classic_control/CartPole-v1.yaml b/xuance/configs/qrdqn/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/qrdqn/classic_control/CartPole-v1.yaml rename to xuance/configs/qrdqn/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/qrdqn/classic_control/MountainCar-v0.yaml b/xuance/configs/qrdqn/classic_control/MountainCar-v0.yaml similarity index 100% rename from xuanpolicy/configs/qrdqn/classic_control/MountainCar-v0.yaml rename to xuance/configs/qrdqn/classic_control/MountainCar-v0.yaml diff --git a/xuanpolicy/configs/qtran/mpe/simple_spread_v3.yaml b/xuance/configs/qtran/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/qtran/mpe/simple_spread_v3.yaml rename to xuance/configs/qtran/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/random/mpe/simple_adversary.yaml b/xuance/configs/random/mpe/simple_adversary.yaml similarity index 100% rename from xuanpolicy/configs/random/mpe/simple_adversary.yaml rename to xuance/configs/random/mpe/simple_adversary.yaml diff --git a/xuanpolicy/configs/random/mpe/simple_push.yaml b/xuance/configs/random/mpe/simple_push.yaml similarity index 100% rename from xuanpolicy/configs/random/mpe/simple_push.yaml rename to xuance/configs/random/mpe/simple_push.yaml diff --git a/xuanpolicy/configs/random/mpe/simple_spread.yaml b/xuance/configs/random/mpe/simple_spread.yaml similarity index 100% rename from xuanpolicy/configs/random/mpe/simple_spread.yaml rename to xuance/configs/random/mpe/simple_spread.yaml diff --git a/xuanpolicy/configs/sac/atari.yaml b/xuance/configs/sac/atari.yaml similarity index 100% rename from xuanpolicy/configs/sac/atari.yaml rename to xuance/configs/sac/atari.yaml diff --git a/xuanpolicy/configs/sac/box2d/BipedalWalker-v3.yaml b/xuance/configs/sac/box2d/BipedalWalker-v3.yaml similarity index 100% rename from xuanpolicy/configs/sac/box2d/BipedalWalker-v3.yaml rename to xuance/configs/sac/box2d/BipedalWalker-v3.yaml diff --git a/xuanpolicy/configs/sac/box2d/LunarLander-v2.yaml b/xuance/configs/sac/box2d/LunarLander-v2.yaml similarity index 100% rename from xuanpolicy/configs/sac/box2d/LunarLander-v2.yaml rename to xuance/configs/sac/box2d/LunarLander-v2.yaml diff --git a/xuanpolicy/configs/sac/classic_control/Acrobot-v1.yaml b/xuance/configs/sac/classic_control/Acrobot-v1.yaml similarity index 100% rename from xuanpolicy/configs/sac/classic_control/Acrobot-v1.yaml rename to xuance/configs/sac/classic_control/Acrobot-v1.yaml diff --git a/xuanpolicy/configs/sac/classic_control/CartPole-v1.yaml b/xuance/configs/sac/classic_control/CartPole-v1.yaml similarity index 100% rename from xuanpolicy/configs/sac/classic_control/CartPole-v1.yaml rename to xuance/configs/sac/classic_control/CartPole-v1.yaml diff --git a/xuanpolicy/configs/sac/classic_control/MountainCar-v0.yaml b/xuance/configs/sac/classic_control/MountainCar-v0.yaml similarity index 100% rename from xuanpolicy/configs/sac/classic_control/MountainCar-v0.yaml rename to xuance/configs/sac/classic_control/MountainCar-v0.yaml diff --git a/xuanpolicy/configs/sac/classic_control/Pendulum-v1.yaml b/xuance/configs/sac/classic_control/Pendulum-v1.yaml similarity index 100% rename from xuanpolicy/configs/sac/classic_control/Pendulum-v1.yaml rename to xuance/configs/sac/classic_control/Pendulum-v1.yaml diff --git a/xuanpolicy/configs/sac/mujoco.yaml b/xuance/configs/sac/mujoco.yaml similarity index 100% rename from xuanpolicy/configs/sac/mujoco.yaml rename to xuance/configs/sac/mujoco.yaml diff --git a/xuanpolicy/configs/spdqn/Platform-v0.yaml b/xuance/configs/spdqn/Platform-v0.yaml similarity index 100% rename from xuanpolicy/configs/spdqn/Platform-v0.yaml rename to xuance/configs/spdqn/Platform-v0.yaml diff --git a/xuanpolicy/configs/td3/box2d/BipedalWalker-v3.yaml b/xuance/configs/td3/box2d/BipedalWalker-v3.yaml similarity index 100% rename from xuanpolicy/configs/td3/box2d/BipedalWalker-v3.yaml rename to xuance/configs/td3/box2d/BipedalWalker-v3.yaml diff --git a/xuanpolicy/configs/td3/classic_control/Pendulum-v1.yaml b/xuance/configs/td3/classic_control/Pendulum-v1.yaml similarity index 100% rename from xuanpolicy/configs/td3/classic_control/Pendulum-v1.yaml rename to xuance/configs/td3/classic_control/Pendulum-v1.yaml diff --git a/xuanpolicy/configs/td3/mujoco.yaml b/xuance/configs/td3/mujoco.yaml similarity index 100% rename from xuanpolicy/configs/td3/mujoco.yaml rename to xuance/configs/td3/mujoco.yaml diff --git a/xuanpolicy/configs/vdac/mpe/simple_spread_v3.yaml b/xuance/configs/vdac/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/vdac/mpe/simple_spread_v3.yaml rename to xuance/configs/vdac/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/vdac/sc2/25m.yaml b/xuance/configs/vdac/sc2/25m.yaml similarity index 100% rename from xuanpolicy/configs/vdac/sc2/25m.yaml rename to xuance/configs/vdac/sc2/25m.yaml diff --git a/xuanpolicy/configs/vdac/sc2/2m_vs_1z.yaml b/xuance/configs/vdac/sc2/2m_vs_1z.yaml similarity index 100% rename from xuanpolicy/configs/vdac/sc2/2m_vs_1z.yaml rename to xuance/configs/vdac/sc2/2m_vs_1z.yaml diff --git a/xuanpolicy/configs/vdac/sc2/3m.yaml b/xuance/configs/vdac/sc2/3m.yaml similarity index 100% rename from xuanpolicy/configs/vdac/sc2/3m.yaml rename to xuance/configs/vdac/sc2/3m.yaml diff --git a/xuanpolicy/configs/vdac/sc2/5m_vs_6m.yaml b/xuance/configs/vdac/sc2/5m_vs_6m.yaml similarity index 100% rename from xuanpolicy/configs/vdac/sc2/5m_vs_6m.yaml rename to xuance/configs/vdac/sc2/5m_vs_6m.yaml diff --git a/xuanpolicy/configs/vdac/sc2/8m.yaml b/xuance/configs/vdac/sc2/8m.yaml similarity index 100% rename from xuanpolicy/configs/vdac/sc2/8m.yaml rename to xuance/configs/vdac/sc2/8m.yaml diff --git a/xuanpolicy/configs/vdac/sc2/8m_vs_9m.yaml b/xuance/configs/vdac/sc2/8m_vs_9m.yaml similarity index 100% rename from xuanpolicy/configs/vdac/sc2/8m_vs_9m.yaml rename to xuance/configs/vdac/sc2/8m_vs_9m.yaml diff --git a/xuanpolicy/configs/vdac/sc2/MMM2.yaml b/xuance/configs/vdac/sc2/MMM2.yaml similarity index 100% rename from xuanpolicy/configs/vdac/sc2/MMM2.yaml rename to xuance/configs/vdac/sc2/MMM2.yaml diff --git a/xuanpolicy/configs/vdac/sc2/corridor.yaml b/xuance/configs/vdac/sc2/corridor.yaml similarity index 100% rename from xuanpolicy/configs/vdac/sc2/corridor.yaml rename to xuance/configs/vdac/sc2/corridor.yaml diff --git a/xuanpolicy/configs/vdn/football/3v1.yaml b/xuance/configs/vdn/football/3v1.yaml similarity index 100% rename from xuanpolicy/configs/vdn/football/3v1.yaml rename to xuance/configs/vdn/football/3v1.yaml diff --git a/xuanpolicy/configs/vdn/mpe/simple_spread_v3.yaml b/xuance/configs/vdn/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/vdn/mpe/simple_spread_v3.yaml rename to xuance/configs/vdn/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/vdn/sc2/25m.yaml b/xuance/configs/vdn/sc2/25m.yaml similarity index 100% rename from xuanpolicy/configs/vdn/sc2/25m.yaml rename to xuance/configs/vdn/sc2/25m.yaml diff --git a/xuanpolicy/configs/vdn/sc2/2m_vs_1z.yaml b/xuance/configs/vdn/sc2/2m_vs_1z.yaml similarity index 100% rename from xuanpolicy/configs/vdn/sc2/2m_vs_1z.yaml rename to xuance/configs/vdn/sc2/2m_vs_1z.yaml diff --git a/xuanpolicy/configs/vdn/sc2/3m.yaml b/xuance/configs/vdn/sc2/3m.yaml similarity index 100% rename from xuanpolicy/configs/vdn/sc2/3m.yaml rename to xuance/configs/vdn/sc2/3m.yaml diff --git a/xuanpolicy/configs/vdn/sc2/5m_vs_6m.yaml b/xuance/configs/vdn/sc2/5m_vs_6m.yaml similarity index 100% rename from xuanpolicy/configs/vdn/sc2/5m_vs_6m.yaml rename to xuance/configs/vdn/sc2/5m_vs_6m.yaml diff --git a/xuanpolicy/configs/vdn/sc2/8m.yaml b/xuance/configs/vdn/sc2/8m.yaml similarity index 100% rename from xuanpolicy/configs/vdn/sc2/8m.yaml rename to xuance/configs/vdn/sc2/8m.yaml diff --git a/xuanpolicy/configs/vdn/sc2/8m_vs_9m.yaml b/xuance/configs/vdn/sc2/8m_vs_9m.yaml similarity index 100% rename from xuanpolicy/configs/vdn/sc2/8m_vs_9m.yaml rename to xuance/configs/vdn/sc2/8m_vs_9m.yaml diff --git a/xuanpolicy/configs/vdn/sc2/MMM2.yaml b/xuance/configs/vdn/sc2/MMM2.yaml similarity index 100% rename from xuanpolicy/configs/vdn/sc2/MMM2.yaml rename to xuance/configs/vdn/sc2/MMM2.yaml diff --git a/xuanpolicy/configs/vdn/sc2/corridor.yaml b/xuance/configs/vdn/sc2/corridor.yaml similarity index 100% rename from xuanpolicy/configs/vdn/sc2/corridor.yaml rename to xuance/configs/vdn/sc2/corridor.yaml diff --git a/xuanpolicy/configs/wqmix/mpe/simple_spread_v3.yaml b/xuance/configs/wqmix/mpe/simple_spread_v3.yaml similarity index 100% rename from xuanpolicy/configs/wqmix/mpe/simple_spread_v3.yaml rename to xuance/configs/wqmix/mpe/simple_spread_v3.yaml diff --git a/xuanpolicy/configs/wqmix/sc2/25m.yaml b/xuance/configs/wqmix/sc2/25m.yaml similarity index 100% rename from xuanpolicy/configs/wqmix/sc2/25m.yaml rename to xuance/configs/wqmix/sc2/25m.yaml diff --git a/xuanpolicy/configs/wqmix/sc2/2m_vs_1z.yaml b/xuance/configs/wqmix/sc2/2m_vs_1z.yaml similarity index 100% rename from xuanpolicy/configs/wqmix/sc2/2m_vs_1z.yaml rename to xuance/configs/wqmix/sc2/2m_vs_1z.yaml diff --git a/xuanpolicy/configs/wqmix/sc2/3m.yaml b/xuance/configs/wqmix/sc2/3m.yaml similarity index 100% rename from xuanpolicy/configs/wqmix/sc2/3m.yaml rename to xuance/configs/wqmix/sc2/3m.yaml diff --git a/xuanpolicy/configs/wqmix/sc2/5m_vs_6m.yaml b/xuance/configs/wqmix/sc2/5m_vs_6m.yaml similarity index 100% rename from xuanpolicy/configs/wqmix/sc2/5m_vs_6m.yaml rename to xuance/configs/wqmix/sc2/5m_vs_6m.yaml diff --git a/xuanpolicy/configs/wqmix/sc2/8m.yaml b/xuance/configs/wqmix/sc2/8m.yaml similarity index 100% rename from xuanpolicy/configs/wqmix/sc2/8m.yaml rename to xuance/configs/wqmix/sc2/8m.yaml diff --git a/xuanpolicy/configs/wqmix/sc2/8m_vs_9m.yaml b/xuance/configs/wqmix/sc2/8m_vs_9m.yaml similarity index 100% rename from xuanpolicy/configs/wqmix/sc2/8m_vs_9m.yaml rename to xuance/configs/wqmix/sc2/8m_vs_9m.yaml diff --git a/xuanpolicy/configs/wqmix/sc2/MMM2.yaml b/xuance/configs/wqmix/sc2/MMM2.yaml similarity index 100% rename from xuanpolicy/configs/wqmix/sc2/MMM2.yaml rename to xuance/configs/wqmix/sc2/MMM2.yaml diff --git a/xuanpolicy/configs/wqmix/sc2/corridor.yaml b/xuance/configs/wqmix/sc2/corridor.yaml similarity index 100% rename from xuanpolicy/configs/wqmix/sc2/corridor.yaml rename to xuance/configs/wqmix/sc2/corridor.yaml diff --git a/xuanpolicy/environment/__init__.py b/xuance/environment/__init__.py similarity index 74% rename from xuanpolicy/environment/__init__.py rename to xuance/environment/__init__.py index 2c7eaf7e8..2162dd261 100644 --- a/xuanpolicy/environment/__init__.py +++ b/xuance/environment/__init__.py @@ -1,14 +1,14 @@ from argparse import Namespace -from xuanpolicy.environment.gym.gym_env import Gym_Env, MountainCar +from xuance.environment.gym.gym_env import Gym_Env, MountainCar from .pettingzoo import PETTINGZOO_ENVIRONMENTS from .vector_envs.vector_env import VecEnv -from xuanpolicy.environment.gym.gym_vec_env import DummyVecEnv_Gym, DummyVecEnv_Atari, SubprocVecEnv_Gym, SubprocVecEnv_Atari -from xuanpolicy.environment.pettingzoo.pettingzoo_vec_env import DummyVecEnv_Pettingzoo -from xuanpolicy.environment.magent2.magent_vec_env import DummyVecEnv_MAgent -from xuanpolicy.environment.starcraft2.sc2_vec_env import SubprocVecEnv_StarCraft2 -from xuanpolicy.environment.football.gfootball_vec_env import DummyVecEnv_GFootball +from xuance.environment.gym.gym_vec_env import DummyVecEnv_Gym, DummyVecEnv_Atari, SubprocVecEnv_Gym, SubprocVecEnv_Atari +from xuance.environment.pettingzoo.pettingzoo_vec_env import DummyVecEnv_Pettingzoo +from xuance.environment.magent2.magent_vec_env import DummyVecEnv_MAgent +from xuance.environment.starcraft2.sc2_vec_env import SubprocVecEnv_StarCraft2 +from xuance.environment.football.gfootball_vec_env import DummyVecEnv_GFootball from .vector_envs.subproc_vec_env import SubprocVecEnv @@ -16,18 +16,18 @@ def make_envs(config: Namespace): def _thunk(): if config.env_name in PETTINGZOO_ENVIRONMENTS: - from xuanpolicy.environment.pettingzoo.pettingzoo_env import PettingZoo_Env + from xuance.environment.pettingzoo.pettingzoo_env import PettingZoo_Env env = PettingZoo_Env(config.env_name, config.env_id, config.seed, continuous=config.continuous_action, render_mode=config.render_mode) elif config.env_name == "StarCraft2": - from xuanpolicy.environment.starcraft2.sc2_env import StarCraft2_Env + from xuance.environment.starcraft2.sc2_env import StarCraft2_Env env = StarCraft2_Env(map_name=config.env_id) elif config.env_name == "Football": - from xuanpolicy.environment.football.gfootball_env import GFootball_Env + from xuance.environment.football.gfootball_env import GFootball_Env env = GFootball_Env(config) elif config.env_name == "MAgent2": - from xuanpolicy.environment.magent2.magent_env import MAgent_Env + from xuance.environment.magent2.magent_env import MAgent_Env env = MAgent_Env(config.env_id, config.seed, minimap_mode=config.minimap_mode, max_cycles=config.max_cycles, @@ -35,7 +35,7 @@ def _thunk(): map_size=config.map_size, render_mode=config.render_mode) elif config.env_name == "Atari": - from xuanpolicy.environment.gym.gym_env import Atari_Env + from xuance.environment.gym.gym_env import Atari_Env env = Atari_Env(config.env_id, config.seed, config.render_mode, config.obs_type, config.frame_skip, config.num_stack, config.img_size, config.noop_max) elif config.env_id.__contains__("MountainCar"): diff --git a/xuanpolicy/environment/football/__init__.py b/xuance/environment/football/__init__.py similarity index 100% rename from xuanpolicy/environment/football/__init__.py rename to xuance/environment/football/__init__.py diff --git a/xuanpolicy/environment/football/gfootball_env.py b/xuance/environment/football/gfootball_env.py similarity index 100% rename from xuanpolicy/environment/football/gfootball_env.py rename to xuance/environment/football/gfootball_env.py diff --git a/xuanpolicy/environment/football/gfootball_vec_env.py b/xuance/environment/football/gfootball_vec_env.py similarity index 96% rename from xuanpolicy/environment/football/gfootball_vec_env.py rename to xuance/environment/football/gfootball_vec_env.py index 490367ab2..199286437 100644 --- a/xuanpolicy/environment/football/gfootball_vec_env.py +++ b/xuance/environment/football/gfootball_vec_env.py @@ -1,5 +1,5 @@ -from xuanpolicy.environment.vector_envs.vector_env import VecEnv, AlreadySteppingError, NotSteppingError -from xuanpolicy.common import combined_shape +from xuance.environment.vector_envs.vector_env import VecEnv, AlreadySteppingError, NotSteppingError +from xuance.common import combined_shape from gymnasium.spaces import Discrete, Box import numpy as np diff --git a/xuanpolicy/environment/football/raw_env.py b/xuance/environment/football/raw_env.py similarity index 100% rename from xuanpolicy/environment/football/raw_env.py rename to xuance/environment/football/raw_env.py diff --git a/xuanpolicy/environment/gym/__init__.py b/xuance/environment/gym/__init__.py similarity index 100% rename from xuanpolicy/environment/gym/__init__.py rename to xuance/environment/gym/__init__.py diff --git a/xuanpolicy/environment/gym/gym_env.py b/xuance/environment/gym/gym_env.py similarity index 100% rename from xuanpolicy/environment/gym/gym_env.py rename to xuance/environment/gym/gym_env.py diff --git a/xuanpolicy/environment/gym/gym_vec_env.py b/xuance/environment/gym/gym_vec_env.py similarity index 97% rename from xuanpolicy/environment/gym/gym_vec_env.py rename to xuance/environment/gym/gym_vec_env.py index 529d46d23..2945b8953 100644 --- a/xuanpolicy/environment/gym/gym_vec_env.py +++ b/xuance/environment/gym/gym_vec_env.py @@ -1,9 +1,9 @@ -from xuanpolicy.environment.vector_envs.vector_env import VecEnv, AlreadySteppingError, NotSteppingError -from xuanpolicy.common import space2shape, combined_shape +from xuance.environment.vector_envs.vector_env import VecEnv, AlreadySteppingError, NotSteppingError +from xuance.common import space2shape, combined_shape from gym.spaces import Dict import numpy as np import multiprocessing as mp -from xuanpolicy.environment.vector_envs.subproc_vec_env import clear_mpi_env_vars, flatten_list, CloudpickleWrapper +from xuance.environment.vector_envs.subproc_vec_env import clear_mpi_env_vars, flatten_list, CloudpickleWrapper def worker(remote, parent_remote, env_fn_wrappers): diff --git a/xuanpolicy/environment/magent2/__init__.py b/xuance/environment/magent2/__init__.py similarity index 100% rename from xuanpolicy/environment/magent2/__init__.py rename to xuance/environment/magent2/__init__.py diff --git a/xuanpolicy/environment/magent2/builtin/__init__.py b/xuance/environment/magent2/builtin/__init__.py similarity index 100% rename from xuanpolicy/environment/magent2/builtin/__init__.py rename to xuance/environment/magent2/builtin/__init__.py diff --git a/xuanpolicy/environment/magent2/builtin/config/__init__.py b/xuance/environment/magent2/builtin/config/__init__.py similarity index 100% rename from xuanpolicy/environment/magent2/builtin/config/__init__.py rename to xuance/environment/magent2/builtin/config/__init__.py diff --git a/xuanpolicy/environment/magent2/builtin/config/battle.py b/xuance/environment/magent2/builtin/config/battle.py similarity index 100% rename from xuanpolicy/environment/magent2/builtin/config/battle.py rename to xuance/environment/magent2/builtin/config/battle.py diff --git a/xuanpolicy/environment/magent2/builtin/config/double_attack.py b/xuance/environment/magent2/builtin/config/double_attack.py similarity index 100% rename from xuanpolicy/environment/magent2/builtin/config/double_attack.py rename to xuance/environment/magent2/builtin/config/double_attack.py diff --git a/xuanpolicy/environment/magent2/builtin/config/forest.py b/xuance/environment/magent2/builtin/config/forest.py similarity index 100% rename from xuanpolicy/environment/magent2/builtin/config/forest.py rename to xuance/environment/magent2/builtin/config/forest.py diff --git a/xuanpolicy/environment/magent2/builtin/config/pursuit.py b/xuance/environment/magent2/builtin/config/pursuit.py similarity index 100% rename from xuanpolicy/environment/magent2/builtin/config/pursuit.py rename to xuance/environment/magent2/builtin/config/pursuit.py diff --git a/xuanpolicy/environment/magent2/c_lib.py b/xuance/environment/magent2/c_lib.py similarity index 100% rename from xuanpolicy/environment/magent2/c_lib.py rename to xuance/environment/magent2/c_lib.py diff --git a/xuanpolicy/environment/magent2/environment.py b/xuance/environment/magent2/environment.py similarity index 100% rename from xuanpolicy/environment/magent2/environment.py rename to xuance/environment/magent2/environment.py diff --git a/xuanpolicy/environment/magent2/environments/__init__.py b/xuance/environment/magent2/environments/__init__.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/__init__.py rename to xuance/environment/magent2/environments/__init__.py diff --git a/xuanpolicy/environment/magent2/environments/adversarial_pursuit/__init__.py b/xuance/environment/magent2/environments/adversarial_pursuit/__init__.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/adversarial_pursuit/__init__.py rename to xuance/environment/magent2/environments/adversarial_pursuit/__init__.py diff --git a/xuanpolicy/environment/magent2/environments/adversarial_pursuit/adversarial_pursuit.py b/xuance/environment/magent2/environments/adversarial_pursuit/adversarial_pursuit.py similarity index 98% rename from xuanpolicy/environment/magent2/environments/adversarial_pursuit/adversarial_pursuit.py rename to xuance/environment/magent2/environments/adversarial_pursuit/adversarial_pursuit.py index 5414b5d74..c3ad169e4 100644 --- a/xuanpolicy/environment/magent2/environments/adversarial_pursuit/adversarial_pursuit.py +++ b/xuance/environment/magent2/environments/adversarial_pursuit/adversarial_pursuit.py @@ -103,8 +103,8 @@ from gymnasium.utils import EzPickle from pettingzoo.utils.conversions import parallel_to_aec_wrapper -from xuanpolicy.environment import magent2 -from xuanpolicy.environment.magent2.environments.magent_env import magent_parallel_env, make_env +from xuance.environment import magent2 +from xuance.environment.magent2.environments.magent_env import magent_parallel_env, make_env default_map_size = 45 diff --git a/xuanpolicy/environment/magent2/environments/adversarial_pursuit_v4.py b/xuance/environment/magent2/environments/adversarial_pursuit_v4.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/adversarial_pursuit_v4.py rename to xuance/environment/magent2/environments/adversarial_pursuit_v4.py diff --git a/xuanpolicy/environment/magent2/environments/battle/__init__.py b/xuance/environment/magent2/environments/battle/__init__.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/battle/__init__.py rename to xuance/environment/magent2/environments/battle/__init__.py diff --git a/xuanpolicy/environment/magent2/environments/battle/battle.py b/xuance/environment/magent2/environments/battle/battle.py similarity index 98% rename from xuanpolicy/environment/magent2/environments/battle/battle.py rename to xuance/environment/magent2/environments/battle/battle.py index dad1dedd2..eea44471f 100644 --- a/xuanpolicy/environment/magent2/environments/battle/battle.py +++ b/xuance/environment/magent2/environments/battle/battle.py @@ -116,8 +116,8 @@ from gymnasium.utils import EzPickle from pettingzoo.utils.conversions import parallel_to_aec_wrapper -from xuanpolicy.environment import magent2 -from xuanpolicy.environment.magent2.environments.magent_env import magent_parallel_env, make_env +from xuance.environment import magent2 +from xuance.environment.magent2.environments.magent_env import magent_parallel_env, make_env default_map_size = 45 diff --git a/xuanpolicy/environment/magent2/environments/battle_v4.py b/xuance/environment/magent2/environments/battle_v4.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/battle_v4.py rename to xuance/environment/magent2/environments/battle_v4.py diff --git a/xuanpolicy/environment/magent2/environments/battlefield/__init__.py b/xuance/environment/magent2/environments/battlefield/__init__.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/battlefield/__init__.py rename to xuance/environment/magent2/environments/battlefield/__init__.py diff --git a/xuanpolicy/environment/magent2/environments/battlefield/battlefield.py b/xuance/environment/magent2/environments/battlefield/battlefield.py similarity index 97% rename from xuanpolicy/environment/magent2/environments/battlefield/battlefield.py rename to xuance/environment/magent2/environments/battlefield/battlefield.py index e42440b34..c280db5d8 100644 --- a/xuanpolicy/environment/magent2/environments/battlefield/battlefield.py +++ b/xuance/environment/magent2/environments/battlefield/battlefield.py @@ -118,9 +118,9 @@ from gymnasium.utils import EzPickle from pettingzoo.utils.conversions import parallel_to_aec_wrapper -from xuanpolicy.environment import magent2 -from xuanpolicy.environment.magent2.environments.battle.battle import KILL_REWARD, get_config -from xuanpolicy.environment.magent2.environments.magent_env import magent_parallel_env, make_env +from xuance.environment import magent2 +from xuance.environment.magent2.environments.battle.battle import KILL_REWARD, get_config +from xuance.environment.magent2.environments.magent_env import magent_parallel_env, make_env default_map_size = 80 diff --git a/xuanpolicy/environment/magent2/environments/battlefield_v5.py b/xuance/environment/magent2/environments/battlefield_v5.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/battlefield_v5.py rename to xuance/environment/magent2/environments/battlefield_v5.py diff --git a/xuanpolicy/environment/magent2/environments/combined_arms/__init__.py b/xuance/environment/magent2/environments/combined_arms/__init__.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/combined_arms/__init__.py rename to xuance/environment/magent2/environments/combined_arms/__init__.py diff --git a/xuanpolicy/environment/magent2/environments/combined_arms/combined_arms.py b/xuance/environment/magent2/environments/combined_arms/combined_arms.py similarity index 98% rename from xuanpolicy/environment/magent2/environments/combined_arms/combined_arms.py rename to xuance/environment/magent2/environments/combined_arms/combined_arms.py index ea8e536bb..259d98401 100644 --- a/xuanpolicy/environment/magent2/environments/combined_arms/combined_arms.py +++ b/xuance/environment/magent2/environments/combined_arms/combined_arms.py @@ -119,8 +119,8 @@ from gymnasium.utils import EzPickle from pettingzoo.utils.conversions import parallel_to_aec_wrapper -from xuanpolicy.environment import magent2 -from xuanpolicy.environment.magent2.environments.magent_env import magent_parallel_env, make_env +from xuance.environment import magent2 +from xuance.environment.magent2.environments.magent_env import magent_parallel_env, make_env default_map_size = 45 diff --git a/xuanpolicy/environment/magent2/environments/combined_arms_v6.py b/xuance/environment/magent2/environments/combined_arms_v6.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/combined_arms_v6.py rename to xuance/environment/magent2/environments/combined_arms_v6.py diff --git a/xuanpolicy/environment/magent2/environments/gather/__init__.py b/xuance/environment/magent2/environments/gather/__init__.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/gather/__init__.py rename to xuance/environment/magent2/environments/gather/__init__.py diff --git a/xuanpolicy/environment/magent2/environments/gather/gather.py b/xuance/environment/magent2/environments/gather/gather.py similarity index 98% rename from xuanpolicy/environment/magent2/environments/gather/gather.py rename to xuance/environment/magent2/environments/gather/gather.py index bbac4a988..f52b5620e 100644 --- a/xuanpolicy/environment/magent2/environments/gather/gather.py +++ b/xuance/environment/magent2/environments/gather/gather.py @@ -105,8 +105,8 @@ from gymnasium.utils import EzPickle from pettingzoo.utils.conversions import parallel_to_aec_wrapper -from xuanpolicy.environment import magent2 -from xuanpolicy.environment.magent2.environments.magent_env import magent_parallel_env, make_env +from xuance.environment import magent2 +from xuance.environment.magent2.environments.magent_env import magent_parallel_env, make_env map_size = 200 diff --git a/xuanpolicy/environment/magent2/environments/gather_v5.py b/xuance/environment/magent2/environments/gather_v5.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/gather_v5.py rename to xuance/environment/magent2/environments/gather_v5.py diff --git a/xuanpolicy/environment/magent2/environments/magent_env.py b/xuance/environment/magent2/environments/magent_env.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/magent_env.py rename to xuance/environment/magent2/environments/magent_env.py diff --git a/xuanpolicy/environment/magent2/environments/tiger_deer/__init__.py b/xuance/environment/magent2/environments/tiger_deer/__init__.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/tiger_deer/__init__.py rename to xuance/environment/magent2/environments/tiger_deer/__init__.py diff --git a/xuanpolicy/environment/magent2/environments/tiger_deer/tiger_deer.py b/xuance/environment/magent2/environments/tiger_deer/tiger_deer.py similarity index 98% rename from xuanpolicy/environment/magent2/environments/tiger_deer/tiger_deer.py rename to xuance/environment/magent2/environments/tiger_deer/tiger_deer.py index 94ffa97aa..fbdd04409 100644 --- a/xuanpolicy/environment/magent2/environments/tiger_deer/tiger_deer.py +++ b/xuance/environment/magent2/environments/tiger_deer/tiger_deer.py @@ -89,8 +89,8 @@ from gymnasium.utils import EzPickle from pettingzoo.utils.conversions import parallel_to_aec_wrapper -from xuanpolicy.environment import magent2 -from xuanpolicy.environment.magent2.environments.magent_env import magent_parallel_env, make_env +from xuance.environment import magent2 +from xuance.environment.magent2.environments.magent_env import magent_parallel_env, make_env default_map_size = 45 diff --git a/xuanpolicy/environment/magent2/environments/tiger_deer_v4.py b/xuance/environment/magent2/environments/tiger_deer_v4.py similarity index 100% rename from xuanpolicy/environment/magent2/environments/tiger_deer_v4.py rename to xuance/environment/magent2/environments/tiger_deer_v4.py diff --git a/xuanpolicy/environment/magent2/gridworld.py b/xuance/environment/magent2/gridworld.py similarity index 100% rename from xuanpolicy/environment/magent2/gridworld.py rename to xuance/environment/magent2/gridworld.py diff --git a/xuanpolicy/environment/magent2/libmagent.so b/xuance/environment/magent2/libmagent.so similarity index 100% rename from xuanpolicy/environment/magent2/libmagent.so rename to xuance/environment/magent2/libmagent.so diff --git a/xuanpolicy/environment/magent2/magent.dll b/xuance/environment/magent2/magent.dll similarity index 100% rename from xuanpolicy/environment/magent2/magent.dll rename to xuance/environment/magent2/magent.dll diff --git a/xuanpolicy/environment/magent2/magent_env.py b/xuance/environment/magent2/magent_env.py similarity index 92% rename from xuanpolicy/environment/magent2/magent_env.py rename to xuance/environment/magent2/magent_env.py index f5afca9eb..54d9f5c4a 100644 --- a/xuanpolicy/environment/magent2/magent_env.py +++ b/xuance/environment/magent2/magent_env.py @@ -1,13 +1,13 @@ from pettingzoo.utils.env import ParallelEnv -from xuanpolicy.environment.pettingzoo.pettingzoo_env import PettingZoo_Env -from xuanpolicy.environment.magent2 import AGENT_NAME_DICT +from xuance.environment.pettingzoo.pettingzoo_env import PettingZoo_Env +from xuance.environment.magent2 import AGENT_NAME_DICT import importlib class MAgent_Env(PettingZoo_Env, ParallelEnv): metadata = {"render_modes": ["human"], "name": "rps_v2"} def __init__(self, env_id: str, seed: int, **kwargs): - scenario = importlib.import_module('xuanpolicy.environment.magent2.environments.' + env_id) + scenario = importlib.import_module('xuance.environment.magent2.environments.' + env_id) if env_id in ["adversarial_pursuit_v4"]: kwargs['minimap_mode'] = False diff --git a/xuanpolicy/environment/magent2/magent_vec_env.py b/xuance/environment/magent2/magent_vec_env.py similarity index 96% rename from xuanpolicy/environment/magent2/magent_vec_env.py rename to xuance/environment/magent2/magent_vec_env.py index 47e84d403..b948fd6c7 100644 --- a/xuanpolicy/environment/magent2/magent_vec_env.py +++ b/xuance/environment/magent2/magent_vec_env.py @@ -1,8 +1,8 @@ import copy -from xuanpolicy.environment.vector_envs.vector_env import VecEnv, AlreadySteppingError, NotSteppingError -from xuanpolicy.environment.vector_envs.env_utils import obs_n_space_info -from xuanpolicy.environment.pettingzoo.pettingzoo_vec_env import DummyVecEnv_Pettingzoo +from xuance.environment.vector_envs.vector_env import VecEnv, AlreadySteppingError, NotSteppingError +from xuance.environment.vector_envs.env_utils import obs_n_space_info +from xuance.environment.pettingzoo.pettingzoo_vec_env import DummyVecEnv_Pettingzoo from operator import itemgetter import numpy as np import time diff --git a/xuanpolicy/environment/magent2/render.py b/xuance/environment/magent2/render.py similarity index 100% rename from xuanpolicy/environment/magent2/render.py rename to xuance/environment/magent2/render.py diff --git a/xuanpolicy/environment/magent2/utility.py b/xuance/environment/magent2/utility.py similarity index 100% rename from xuanpolicy/environment/magent2/utility.py rename to xuance/environment/magent2/utility.py diff --git a/xuanpolicy/environment/pettingzoo/__init__.py b/xuance/environment/pettingzoo/__init__.py similarity index 100% rename from xuanpolicy/environment/pettingzoo/__init__.py rename to xuance/environment/pettingzoo/__init__.py diff --git a/xuanpolicy/environment/pettingzoo/pettingzoo_env.py b/xuance/environment/pettingzoo/pettingzoo_env.py similarity index 98% rename from xuanpolicy/environment/pettingzoo/pettingzoo_env.py rename to xuance/environment/pettingzoo/pettingzoo_env.py index 894d0fd94..917ddd157 100644 --- a/xuanpolicy/environment/pettingzoo/pettingzoo_env.py +++ b/xuance/environment/pettingzoo/pettingzoo_env.py @@ -2,7 +2,7 @@ import numpy as np import ctypes import importlib -from xuanpolicy.environment.pettingzoo import AGENT_NAME_DICT +from xuance.environment.pettingzoo import AGENT_NAME_DICT class PettingZoo_Env(ParallelEnv): diff --git a/xuanpolicy/environment/pettingzoo/pettingzoo_vec_env.py b/xuance/environment/pettingzoo/pettingzoo_vec_env.py similarity index 96% rename from xuanpolicy/environment/pettingzoo/pettingzoo_vec_env.py rename to xuance/environment/pettingzoo/pettingzoo_vec_env.py index 240d43880..c88e23cc1 100644 --- a/xuanpolicy/environment/pettingzoo/pettingzoo_vec_env.py +++ b/xuance/environment/pettingzoo/pettingzoo_vec_env.py @@ -1,6 +1,6 @@ -from xuanpolicy.environment.vector_envs.vector_env import VecEnv, AlreadySteppingError, NotSteppingError -from xuanpolicy.environment.vector_envs.env_utils import obs_n_space_info -from xuanpolicy.environment.gym.gym_vec_env import DummyVecEnv_Gym +from xuance.environment.vector_envs.vector_env import VecEnv, AlreadySteppingError, NotSteppingError +from xuance.environment.vector_envs.env_utils import obs_n_space_info +from xuance.environment.gym.gym_vec_env import DummyVecEnv_Gym from operator import itemgetter from gymnasium.spaces.box import Box import numpy as np diff --git a/xuanpolicy/environment/starcraft2/__init__.py b/xuance/environment/starcraft2/__init__.py similarity index 100% rename from xuanpolicy/environment/starcraft2/__init__.py rename to xuance/environment/starcraft2/__init__.py diff --git a/xuanpolicy/environment/starcraft2/sc2_env.py b/xuance/environment/starcraft2/sc2_env.py similarity index 100% rename from xuanpolicy/environment/starcraft2/sc2_env.py rename to xuance/environment/starcraft2/sc2_env.py diff --git a/xuanpolicy/environment/starcraft2/sc2_vec_env.py b/xuance/environment/starcraft2/sc2_vec_env.py similarity index 98% rename from xuanpolicy/environment/starcraft2/sc2_vec_env.py rename to xuance/environment/starcraft2/sc2_vec_env.py index 194859113..5dedbe73b 100644 --- a/xuanpolicy/environment/starcraft2/sc2_vec_env.py +++ b/xuance/environment/starcraft2/sc2_vec_env.py @@ -1,9 +1,9 @@ -from xuanpolicy.common import combined_shape +from xuance.common import combined_shape from gymnasium.spaces import Discrete, Box import numpy as np import multiprocessing as mp -from xuanpolicy.environment.vector_envs.subproc_vec_env import clear_mpi_env_vars, flatten_list, CloudpickleWrapper -from xuanpolicy.environment.vector_envs.vector_env import VecEnv +from xuance.environment.vector_envs.subproc_vec_env import clear_mpi_env_vars, flatten_list, CloudpickleWrapper +from xuance.environment.vector_envs.vector_env import VecEnv def worker(remote, parent_remote, env_fn_wrappers): diff --git a/xuanpolicy/environment/vector_envs/__init__.py b/xuance/environment/vector_envs/__init__.py similarity index 100% rename from xuanpolicy/environment/vector_envs/__init__.py rename to xuance/environment/vector_envs/__init__.py diff --git a/xuanpolicy/environment/vector_envs/env_utils.py b/xuance/environment/vector_envs/env_utils.py similarity index 100% rename from xuanpolicy/environment/vector_envs/env_utils.py rename to xuance/environment/vector_envs/env_utils.py diff --git a/xuanpolicy/environment/vector_envs/subproc_vec_env.py b/xuance/environment/vector_envs/subproc_vec_env.py similarity index 100% rename from xuanpolicy/environment/vector_envs/subproc_vec_env.py rename to xuance/environment/vector_envs/subproc_vec_env.py diff --git a/xuanpolicy/environment/vector_envs/vector_env.py b/xuance/environment/vector_envs/vector_env.py similarity index 100% rename from xuanpolicy/environment/vector_envs/vector_env.py rename to xuance/environment/vector_envs/vector_env.py diff --git a/xuanpolicy/mindspore/__init__.py b/xuance/mindspore/__init__.py similarity index 100% rename from xuanpolicy/mindspore/__init__.py rename to xuance/mindspore/__init__.py diff --git a/xuanpolicy/mindspore/agents/__init__.py b/xuance/mindspore/agents/__init__.py similarity index 89% rename from xuanpolicy/mindspore/agents/__init__.py rename to xuance/mindspore/agents/__init__.py index ee9636647..28086b9d9 100644 --- a/xuanpolicy/mindspore/agents/__init__.py +++ b/xuance/mindspore/agents/__init__.py @@ -7,14 +7,14 @@ import mindspore as ms import mindspore.nn as nn from mindspore import context -from xuanpolicy.common import * -from xuanpolicy.environment import * -from xuanpolicy.mindspore.learners import * -from xuanpolicy.mindspore.utils import * -from xuanpolicy.mindspore.policies import * -from xuanpolicy.mindspore.policies import REGISTRY as REGISTRY_Policy -from xuanpolicy.mindspore.utils.input_reformat import get_repre_in, get_policy_in_marl -from xuanpolicy.mindspore.representations import REGISTRY as REGISTRY_Representation +from xuance.common import * +from xuance.environment import * +from xuance.mindspore.learners import * +from xuance.mindspore.utils import * +from xuance.mindspore.policies import * +from xuance.mindspore.policies import REGISTRY as REGISTRY_Policy +from xuance.mindspore.utils.input_reformat import get_repre_in, get_policy_in_marl +from xuance.mindspore.representations import REGISTRY as REGISTRY_Representation from mindspore.nn import Adam from mindspore.nn.learning_rate_schedule import ExponentialDecayLR as lr_decay_model diff --git a/xuanpolicy/mindspore/agents/agent.py b/xuance/mindspore/agents/agent.py similarity index 96% rename from xuanpolicy/mindspore/agents/agent.py rename to xuance/mindspore/agents/agent.py index 87505d822..85adfd4a9 100644 --- a/xuanpolicy/mindspore/agents/agent.py +++ b/xuance/mindspore/agents/agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class Agent(ABC): diff --git a/xuanpolicy/mindspore/agents/agents_marl.py b/xuance/mindspore/agents/agents_marl.py similarity index 98% rename from xuanpolicy/mindspore/agents/agents_marl.py rename to xuance/mindspore/agents/agents_marl.py index 8d9a95af6..71db76e75 100644 --- a/xuanpolicy/mindspore/agents/agents_marl.py +++ b/xuance/mindspore/agents/agents_marl.py @@ -1,7 +1,7 @@ import mindspore as ms import mindspore.ops as ops from mindspore import Tensor -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class MARLAgents(object): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/__init__.py b/xuance/mindspore/agents/multi_agent_rl/__init__.py similarity index 100% rename from xuanpolicy/mindspore/agents/multi_agent_rl/__init__.py rename to xuance/mindspore/agents/multi_agent_rl/__init__.py diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/coma_agents.py b/xuance/mindspore/agents/multi_agent_rl/coma_agents.py similarity index 97% rename from xuanpolicy/mindspore/agents/multi_agent_rl/coma_agents.py rename to xuance/mindspore/agents/multi_agent_rl/coma_agents.py index 418e15ed5..3ea380dce 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/coma_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/coma_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.agents import * -from xuanpolicy.mindspore.agents.agents_marl import linear_decay_or_increase +from xuance.mindspore.agents import * +from xuance.mindspore.agents.agents_marl import linear_decay_or_increase class COMA_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/dcg_agents.py b/xuance/mindspore/agents/multi_agent_rl/dcg_agents.py similarity index 97% rename from xuanpolicy/mindspore/agents/multi_agent_rl/dcg_agents.py rename to xuance/mindspore/agents/multi_agent_rl/dcg_agents.py index 6a497ac0a..b6f9e0998 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/dcg_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/dcg_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.agents import * -from xuanpolicy.mindspore.agents.agents_marl import linear_decay_or_increase +from xuance.mindspore.agents import * +from xuance.mindspore.agents.agents_marl import linear_decay_or_increase class DCG_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/iddpg_agents.py b/xuance/mindspore/agents/multi_agent_rl/iddpg_agents.py similarity index 99% rename from xuanpolicy/mindspore/agents/multi_agent_rl/iddpg_agents.py rename to xuance/mindspore/agents/multi_agent_rl/iddpg_agents.py index 297a2c10b..9cee091dd 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/iddpg_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/iddpg_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class IDDPG_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/iql_agents.py b/xuance/mindspore/agents/multi_agent_rl/iql_agents.py similarity index 97% rename from xuanpolicy/mindspore/agents/multi_agent_rl/iql_agents.py rename to xuance/mindspore/agents/multi_agent_rl/iql_agents.py index 86681d193..ee01bb677 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/iql_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/iql_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.agents import * -from xuanpolicy.mindspore.agents.agents_marl import linear_decay_or_increase +from xuance.mindspore.agents import * +from xuance.mindspore.agents.agents_marl import linear_decay_or_increase class IQL_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/isac_agents.py b/xuance/mindspore/agents/multi_agent_rl/isac_agents.py similarity index 99% rename from xuanpolicy/mindspore/agents/multi_agent_rl/isac_agents.py rename to xuance/mindspore/agents/multi_agent_rl/isac_agents.py index 2b2a8bbce..08a01b8f1 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/isac_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/isac_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class ISAC_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/maddpg_agents.py b/xuance/mindspore/agents/multi_agent_rl/maddpg_agents.py similarity index 99% rename from xuanpolicy/mindspore/agents/multi_agent_rl/maddpg_agents.py rename to xuance/mindspore/agents/multi_agent_rl/maddpg_agents.py index ae5b187d8..7f55ffeb5 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/maddpg_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/maddpg_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class MADDPG_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/mappoclip_agents.py b/xuance/mindspore/agents/multi_agent_rl/mappoclip_agents.py similarity index 99% rename from xuanpolicy/mindspore/agents/multi_agent_rl/mappoclip_agents.py rename to xuance/mindspore/agents/multi_agent_rl/mappoclip_agents.py index 026c045f7..2eef01ba0 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/mappoclip_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/mappoclip_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class MAPPO_Clip_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/mappokl_agents.py b/xuance/mindspore/agents/multi_agent_rl/mappokl_agents.py similarity index 99% rename from xuanpolicy/mindspore/agents/multi_agent_rl/mappokl_agents.py rename to xuance/mindspore/agents/multi_agent_rl/mappokl_agents.py index cb1ddc78b..7d50be502 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/mappokl_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/mappokl_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class MAPPO_KL_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/masac_agents.py b/xuance/mindspore/agents/multi_agent_rl/masac_agents.py similarity index 99% rename from xuanpolicy/mindspore/agents/multi_agent_rl/masac_agents.py rename to xuance/mindspore/agents/multi_agent_rl/masac_agents.py index 8e0bb7e3f..23e62dd7c 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/masac_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/masac_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class MASAC_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/matd3_agents.py b/xuance/mindspore/agents/multi_agent_rl/matd3_agents.py similarity index 99% rename from xuanpolicy/mindspore/agents/multi_agent_rl/matd3_agents.py rename to xuance/mindspore/agents/multi_agent_rl/matd3_agents.py index 39c2c06ab..bea56f07a 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/matd3_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/matd3_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class MATD3_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/mfac_agents.py b/xuance/mindspore/agents/multi_agent_rl/mfac_agents.py similarity index 99% rename from xuanpolicy/mindspore/agents/multi_agent_rl/mfac_agents.py rename to xuance/mindspore/agents/multi_agent_rl/mfac_agents.py index fb13cc7aa..a55fd0415 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/mfac_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/mfac_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class MFAC_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/mfq_agents.py b/xuance/mindspore/agents/multi_agent_rl/mfq_agents.py similarity index 97% rename from xuanpolicy/mindspore/agents/multi_agent_rl/mfq_agents.py rename to xuance/mindspore/agents/multi_agent_rl/mfq_agents.py index a75c86f90..9686ebdc2 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/mfq_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/mfq_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.agents import * -from xuanpolicy.mindspore.agents.agents_marl import linear_decay_or_increase +from xuance.mindspore.agents import * +from xuance.mindspore.agents.agents_marl import linear_decay_or_increase class MFQ_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/qmix_agents.py b/xuance/mindspore/agents/multi_agent_rl/qmix_agents.py similarity index 97% rename from xuanpolicy/mindspore/agents/multi_agent_rl/qmix_agents.py rename to xuance/mindspore/agents/multi_agent_rl/qmix_agents.py index e2c06a310..af3b8fe81 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/qmix_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/qmix_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.agents import * -from xuanpolicy.mindspore.agents.agents_marl import linear_decay_or_increase +from xuance.mindspore.agents import * +from xuance.mindspore.agents.agents_marl import linear_decay_or_increase class QMIX_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/qtran_agents.py b/xuance/mindspore/agents/multi_agent_rl/qtran_agents.py similarity index 97% rename from xuanpolicy/mindspore/agents/multi_agent_rl/qtran_agents.py rename to xuance/mindspore/agents/multi_agent_rl/qtran_agents.py index e2bed8dbc..587ce6d94 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/qtran_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/qtran_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.agents import * -from xuanpolicy.mindspore.agents.agents_marl import linear_decay_or_increase +from xuance.mindspore.agents import * +from xuance.mindspore.agents.agents_marl import linear_decay_or_increase class QTRAN_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/vdac_agents.py b/xuance/mindspore/agents/multi_agent_rl/vdac_agents.py similarity index 99% rename from xuanpolicy/mindspore/agents/multi_agent_rl/vdac_agents.py rename to xuance/mindspore/agents/multi_agent_rl/vdac_agents.py index f9ca78c17..6e3ffbf71 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/vdac_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/vdac_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class VDAC_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/vdn_agents.py b/xuance/mindspore/agents/multi_agent_rl/vdn_agents.py similarity index 97% rename from xuanpolicy/mindspore/agents/multi_agent_rl/vdn_agents.py rename to xuance/mindspore/agents/multi_agent_rl/vdn_agents.py index 141fcadaf..a632757d8 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/vdn_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/vdn_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.agents import * -from xuanpolicy.mindspore.agents.agents_marl import linear_decay_or_increase +from xuance.mindspore.agents import * +from xuance.mindspore.agents.agents_marl import linear_decay_or_increase class VDN_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/multi_agent_rl/wqmix_agents.py b/xuance/mindspore/agents/multi_agent_rl/wqmix_agents.py similarity index 97% rename from xuanpolicy/mindspore/agents/multi_agent_rl/wqmix_agents.py rename to xuance/mindspore/agents/multi_agent_rl/wqmix_agents.py index 183a47024..1563fb2c7 100644 --- a/xuanpolicy/mindspore/agents/multi_agent_rl/wqmix_agents.py +++ b/xuance/mindspore/agents/multi_agent_rl/wqmix_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.agents import * -from xuanpolicy.mindspore.agents.agents_marl import linear_decay_or_increase +from xuance.mindspore.agents import * +from xuance.mindspore.agents.agents_marl import linear_decay_or_increase class WQMIX_Agents(MARLAgents): diff --git a/xuanpolicy/mindspore/agents/policy_gradient/__init__.py b/xuance/mindspore/agents/policy_gradient/__init__.py similarity index 100% rename from xuanpolicy/mindspore/agents/policy_gradient/__init__.py rename to xuance/mindspore/agents/policy_gradient/__init__.py diff --git a/xuanpolicy/mindspore/agents/policy_gradient/a2c_agent.py b/xuance/mindspore/agents/policy_gradient/a2c_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/policy_gradient/a2c_agent.py rename to xuance/mindspore/agents/policy_gradient/a2c_agent.py index 18d6af184..3ad9ef164 100644 --- a/xuanpolicy/mindspore/agents/policy_gradient/a2c_agent.py +++ b/xuance/mindspore/agents/policy_gradient/a2c_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class A2C_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/policy_gradient/ddpg_agent.py b/xuance/mindspore/agents/policy_gradient/ddpg_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/policy_gradient/ddpg_agent.py rename to xuance/mindspore/agents/policy_gradient/ddpg_agent.py index cdf743033..a74202e64 100644 --- a/xuanpolicy/mindspore/agents/policy_gradient/ddpg_agent.py +++ b/xuance/mindspore/agents/policy_gradient/ddpg_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class DDPG_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/policy_gradient/mpdqn_agent.py b/xuance/mindspore/agents/policy_gradient/mpdqn_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/policy_gradient/mpdqn_agent.py rename to xuance/mindspore/agents/policy_gradient/mpdqn_agent.py index 5a74d6fdd..6ecafa640 100644 --- a/xuanpolicy/mindspore/agents/policy_gradient/mpdqn_agent.py +++ b/xuance/mindspore/agents/policy_gradient/mpdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * import gym from gym import spaces diff --git a/xuanpolicy/mindspore/agents/policy_gradient/pdqn_agent.py b/xuance/mindspore/agents/policy_gradient/pdqn_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/policy_gradient/pdqn_agent.py rename to xuance/mindspore/agents/policy_gradient/pdqn_agent.py index 8d1086760..0fea9e728 100644 --- a/xuanpolicy/mindspore/agents/policy_gradient/pdqn_agent.py +++ b/xuance/mindspore/agents/policy_gradient/pdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * import gym from gym import spaces diff --git a/xuanpolicy/mindspore/agents/policy_gradient/pg_agent.py b/xuance/mindspore/agents/policy_gradient/pg_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/policy_gradient/pg_agent.py rename to xuance/mindspore/agents/policy_gradient/pg_agent.py index 0f4125376..ede78c895 100644 --- a/xuanpolicy/mindspore/agents/policy_gradient/pg_agent.py +++ b/xuance/mindspore/agents/policy_gradient/pg_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class PG_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/policy_gradient/ppg_agent.py b/xuance/mindspore/agents/policy_gradient/ppg_agent.py similarity index 98% rename from xuanpolicy/mindspore/agents/policy_gradient/ppg_agent.py rename to xuance/mindspore/agents/policy_gradient/ppg_agent.py index 12c8f6252..0e6f5fa84 100644 --- a/xuanpolicy/mindspore/agents/policy_gradient/ppg_agent.py +++ b/xuance/mindspore/agents/policy_gradient/ppg_agent.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.agents import * -from xuanpolicy.mindspore.utils.distributions import CategoricalDistribution +from xuance.mindspore.agents import * +from xuance.mindspore.utils.distributions import CategoricalDistribution class PPG_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/policy_gradient/ppoclip_agent.py b/xuance/mindspore/agents/policy_gradient/ppoclip_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/policy_gradient/ppoclip_agent.py rename to xuance/mindspore/agents/policy_gradient/ppoclip_agent.py index 0ea7aeaa3..e91612c2c 100644 --- a/xuanpolicy/mindspore/agents/policy_gradient/ppoclip_agent.py +++ b/xuance/mindspore/agents/policy_gradient/ppoclip_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class PPOCLIP_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/policy_gradient/ppokl_agent.py b/xuance/mindspore/agents/policy_gradient/ppokl_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/policy_gradient/ppokl_agent.py rename to xuance/mindspore/agents/policy_gradient/ppokl_agent.py index 6938de1a1..182ac5725 100644 --- a/xuanpolicy/mindspore/agents/policy_gradient/ppokl_agent.py +++ b/xuance/mindspore/agents/policy_gradient/ppokl_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class PPOKL_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/policy_gradient/sac_agent.py b/xuance/mindspore/agents/policy_gradient/sac_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/policy_gradient/sac_agent.py rename to xuance/mindspore/agents/policy_gradient/sac_agent.py index 66a74a939..34aa3eae0 100644 --- a/xuanpolicy/mindspore/agents/policy_gradient/sac_agent.py +++ b/xuance/mindspore/agents/policy_gradient/sac_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class SAC_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/policy_gradient/sacdis_agent.py b/xuance/mindspore/agents/policy_gradient/sacdis_agent.py similarity index 98% rename from xuanpolicy/mindspore/agents/policy_gradient/sacdis_agent.py rename to xuance/mindspore/agents/policy_gradient/sacdis_agent.py index 04f8f01fb..727c5aef8 100644 --- a/xuanpolicy/mindspore/agents/policy_gradient/sacdis_agent.py +++ b/xuance/mindspore/agents/policy_gradient/sacdis_agent.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.agents import * -from xuanpolicy.mindspore.utils.distributions import CategoricalDistribution +from xuance.mindspore.agents import * +from xuance.mindspore.utils.distributions import CategoricalDistribution class SACDIS_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/policy_gradient/spdqn_agent.py b/xuance/mindspore/agents/policy_gradient/spdqn_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/policy_gradient/spdqn_agent.py rename to xuance/mindspore/agents/policy_gradient/spdqn_agent.py index 5e064d68d..461caba25 100644 --- a/xuanpolicy/mindspore/agents/policy_gradient/spdqn_agent.py +++ b/xuance/mindspore/agents/policy_gradient/spdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * import gym from gym import spaces diff --git a/xuanpolicy/mindspore/agents/policy_gradient/td3_agent.py b/xuance/mindspore/agents/policy_gradient/td3_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/policy_gradient/td3_agent.py rename to xuance/mindspore/agents/policy_gradient/td3_agent.py index 08d7fe2ae..455ead689 100644 --- a/xuanpolicy/mindspore/agents/policy_gradient/td3_agent.py +++ b/xuance/mindspore/agents/policy_gradient/td3_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class TD3_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/qlearning_family/C51_agent.py b/xuance/mindspore/agents/qlearning_family/C51_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/qlearning_family/C51_agent.py rename to xuance/mindspore/agents/qlearning_family/C51_agent.py index d8160a0c8..470f198f9 100644 --- a/xuanpolicy/mindspore/agents/qlearning_family/C51_agent.py +++ b/xuance/mindspore/agents/qlearning_family/C51_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class C51_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/qlearning_family/__init__.py b/xuance/mindspore/agents/qlearning_family/__init__.py similarity index 100% rename from xuanpolicy/mindspore/agents/qlearning_family/__init__.py rename to xuance/mindspore/agents/qlearning_family/__init__.py diff --git a/xuanpolicy/mindspore/agents/qlearning_family/cdqn_agent.py b/xuance/mindspore/agents/qlearning_family/cdqn_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/qlearning_family/cdqn_agent.py rename to xuance/mindspore/agents/qlearning_family/cdqn_agent.py index f53b7af66..d08705785 100644 --- a/xuanpolicy/mindspore/agents/qlearning_family/cdqn_agent.py +++ b/xuance/mindspore/agents/qlearning_family/cdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class CDQN_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/qlearning_family/cldqn_agent.py b/xuance/mindspore/agents/qlearning_family/cldqn_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/qlearning_family/cldqn_agent.py rename to xuance/mindspore/agents/qlearning_family/cldqn_agent.py index c601a4f21..c1e29927e 100644 --- a/xuanpolicy/mindspore/agents/qlearning_family/cldqn_agent.py +++ b/xuance/mindspore/agents/qlearning_family/cldqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class CLDQN_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/qlearning_family/ddqn_agent.py b/xuance/mindspore/agents/qlearning_family/ddqn_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/qlearning_family/ddqn_agent.py rename to xuance/mindspore/agents/qlearning_family/ddqn_agent.py index 81e45a6e9..99070e6d4 100644 --- a/xuanpolicy/mindspore/agents/qlearning_family/ddqn_agent.py +++ b/xuance/mindspore/agents/qlearning_family/ddqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class DDQN_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/qlearning_family/dqn_agent.py b/xuance/mindspore/agents/qlearning_family/dqn_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/qlearning_family/dqn_agent.py rename to xuance/mindspore/agents/qlearning_family/dqn_agent.py index 53d9e3213..c01634097 100644 --- a/xuanpolicy/mindspore/agents/qlearning_family/dqn_agent.py +++ b/xuance/mindspore/agents/qlearning_family/dqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class DQN_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/qlearning_family/dueldqn_agent.py b/xuance/mindspore/agents/qlearning_family/dueldqn_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/qlearning_family/dueldqn_agent.py rename to xuance/mindspore/agents/qlearning_family/dueldqn_agent.py index e53fab167..98a7c86bf 100644 --- a/xuanpolicy/mindspore/agents/qlearning_family/dueldqn_agent.py +++ b/xuance/mindspore/agents/qlearning_family/dueldqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class DuelDQN_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/qlearning_family/ldqn_agent.py b/xuance/mindspore/agents/qlearning_family/ldqn_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/qlearning_family/ldqn_agent.py rename to xuance/mindspore/agents/qlearning_family/ldqn_agent.py index 583eb6e1f..d752b7333 100644 --- a/xuanpolicy/mindspore/agents/qlearning_family/ldqn_agent.py +++ b/xuance/mindspore/agents/qlearning_family/ldqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class LDQN_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/qlearning_family/noisydqn_agent.py b/xuance/mindspore/agents/qlearning_family/noisydqn_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/qlearning_family/noisydqn_agent.py rename to xuance/mindspore/agents/qlearning_family/noisydqn_agent.py index 10dbc1ca0..2c04ae9f5 100644 --- a/xuanpolicy/mindspore/agents/qlearning_family/noisydqn_agent.py +++ b/xuance/mindspore/agents/qlearning_family/noisydqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class NoisyDQN_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/qlearning_family/perdqn_agent.py b/xuance/mindspore/agents/qlearning_family/perdqn_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/qlearning_family/perdqn_agent.py rename to xuance/mindspore/agents/qlearning_family/perdqn_agent.py index fbea5579a..98414e72c 100644 --- a/xuanpolicy/mindspore/agents/qlearning_family/perdqn_agent.py +++ b/xuance/mindspore/agents/qlearning_family/perdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class PerDQN_Agent(Agent): diff --git a/xuanpolicy/mindspore/agents/qlearning_family/qrdqn_agent.py b/xuance/mindspore/agents/qlearning_family/qrdqn_agent.py similarity index 99% rename from xuanpolicy/mindspore/agents/qlearning_family/qrdqn_agent.py rename to xuance/mindspore/agents/qlearning_family/qrdqn_agent.py index eb93b2e5f..092af44e4 100644 --- a/xuanpolicy/mindspore/agents/qlearning_family/qrdqn_agent.py +++ b/xuance/mindspore/agents/qlearning_family/qrdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.agents import * +from xuance.mindspore.agents import * class QRDQN_Agent(Agent): diff --git a/xuanpolicy/mindspore/learners/__init__.py b/xuance/mindspore/learners/__init__.py similarity index 97% rename from xuanpolicy/mindspore/learners/__init__.py rename to xuance/mindspore/learners/__init__.py index fbd9ce577..3f07f7001 100644 --- a/xuanpolicy/mindspore/learners/__init__.py +++ b/xuance/mindspore/learners/__init__.py @@ -4,7 +4,7 @@ from typing import Sequence, Optional, Callable, Union from gym.spaces import Space, Box, Discrete, Dict from torch.utils.tensorboard import SummaryWriter -from xuanpolicy.mindspore.utils.set_trainer import * +from xuance.mindspore.utils.set_trainer import * from argparse import Namespace from mindspore import Tensor from mindspore.ops import OneHot, GatherD diff --git a/xuanpolicy/mindspore/learners/learner.py b/xuance/mindspore/learners/learner.py similarity index 100% rename from xuanpolicy/mindspore/learners/learner.py rename to xuance/mindspore/learners/learner.py diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/__init__.py b/xuance/mindspore/learners/multi_agent_rl/__init__.py similarity index 100% rename from xuanpolicy/mindspore/learners/multi_agent_rl/__init__.py rename to xuance/mindspore/learners/multi_agent_rl/__init__.py diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/coma_learner.py b/xuance/mindspore/learners/multi_agent_rl/coma_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/multi_agent_rl/coma_learner.py rename to xuance/mindspore/learners/multi_agent_rl/coma_learner.py index c8d4b008d..ff60baed0 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/coma_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/coma_learner.py @@ -3,7 +3,7 @@ Paper link: https://ojs.aaai.org/index.php/AAAI/article/view/11794 Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class COMA_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/dcg_learner.py b/xuance/mindspore/learners/multi_agent_rl/dcg_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/multi_agent_rl/dcg_learner.py rename to xuance/mindspore/learners/multi_agent_rl/dcg_learner.py index 3e39f96db..a989519ca 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/dcg_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/dcg_learner.py @@ -3,7 +3,7 @@ Paper link: http://proceedings.mlr.press/v119/boehmer20a/boehmer20a.pdf Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * import torch_scatter import torch import copy diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/iddpg_learner.py b/xuance/mindspore/learners/multi_agent_rl/iddpg_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/multi_agent_rl/iddpg_learner.py rename to xuance/mindspore/learners/multi_agent_rl/iddpg_learner.py index 2fa71e317..6789edc1c 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/iddpg_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/iddpg_learner.py @@ -2,7 +2,7 @@ Independent Deep Deterministic Policy Gradient (IDDPG) Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class IDDPG_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/iql_learner.py b/xuance/mindspore/learners/multi_agent_rl/iql_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/multi_agent_rl/iql_learner.py rename to xuance/mindspore/learners/multi_agent_rl/iql_learner.py index 2c5c4eeef..563b4522a 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/iql_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/iql_learner.py @@ -2,7 +2,7 @@ Independent Q-learning (IQL) Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class IQL_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/isac_learner.py b/xuance/mindspore/learners/multi_agent_rl/isac_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/multi_agent_rl/isac_learner.py rename to xuance/mindspore/learners/multi_agent_rl/isac_learner.py index c8f072c6f..ebbed67b8 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/isac_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/isac_learner.py @@ -3,7 +3,7 @@ Implementation: Pytorch Creator: Kun Jiang (kjiang@seu.edu.cn) """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class ISAC_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/maddpg_learner.py b/xuance/mindspore/learners/multi_agent_rl/maddpg_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/multi_agent_rl/maddpg_learner.py rename to xuance/mindspore/learners/multi_agent_rl/maddpg_learner.py index e80b2e02e..637c9a27a 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/maddpg_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/maddpg_learner.py @@ -5,7 +5,7 @@ Implementation: MindSpore Trick: Parameter sharing for all agents, with agents' one-hot IDs as actor-critic's inputs. """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class MADDPG_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/mappoclip_learner.py b/xuance/mindspore/learners/multi_agent_rl/mappoclip_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/multi_agent_rl/mappoclip_learner.py rename to xuance/mindspore/learners/multi_agent_rl/mappoclip_learner.py index 45bdffb26..07ae89bd2 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/mappoclip_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/mappoclip_learner.py @@ -4,7 +4,7 @@ https://arxiv.org/pdf/2103.01955.pdf Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class MAPPO_Clip_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/mappokl_learner.py b/xuance/mindspore/learners/multi_agent_rl/mappokl_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/multi_agent_rl/mappokl_learner.py rename to xuance/mindspore/learners/multi_agent_rl/mappokl_learner.py index decc820c1..25467248e 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/mappokl_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/mappokl_learner.py @@ -4,7 +4,7 @@ https://arxiv.org/pdf/2103.01955.pdf Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class MAPPO_KL_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/masac_learner.py b/xuance/mindspore/learners/multi_agent_rl/masac_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/multi_agent_rl/masac_learner.py rename to xuance/mindspore/learners/multi_agent_rl/masac_learner.py index 834b1df0d..cd65a9f35 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/masac_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/masac_learner.py @@ -3,7 +3,7 @@ Implementation: Pytorch Creator: Kun Jiang (kjiang@seu.edu.cn) """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class MASAC_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/matd3_learner.py b/xuance/mindspore/learners/multi_agent_rl/matd3_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/multi_agent_rl/matd3_learner.py rename to xuance/mindspore/learners/multi_agent_rl/matd3_learner.py index ed28db91f..9a0e18f51 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/matd3_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/matd3_learner.py @@ -2,7 +2,7 @@ Multi-Agent TD3 """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class MATD3_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/mfac_learner.py b/xuance/mindspore/learners/multi_agent_rl/mfac_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/multi_agent_rl/mfac_learner.py rename to xuance/mindspore/learners/multi_agent_rl/mfac_learner.py index 61c4016d7..73265fd33 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/mfac_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/mfac_learner.py @@ -4,7 +4,7 @@ http://proceedings.mlr.press/v80/yang18d/yang18d.pdf Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class MFAC_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/mfq_learner.py b/xuance/mindspore/learners/multi_agent_rl/mfq_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/multi_agent_rl/mfq_learner.py rename to xuance/mindspore/learners/multi_agent_rl/mfq_learner.py index 0cc37e8c5..ca608f7a3 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/mfq_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/mfq_learner.py @@ -4,7 +4,7 @@ http://proceedings.mlr.press/v80/yang18d/yang18d.pdf Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class MFQ_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/qmix_learner.py b/xuance/mindspore/learners/multi_agent_rl/qmix_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/multi_agent_rl/qmix_learner.py rename to xuance/mindspore/learners/multi_agent_rl/qmix_learner.py index e5bc62226..4f5e64632 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/qmix_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/qmix_learner.py @@ -4,7 +4,7 @@ http://proceedings.mlr.press/v80/rashid18a/rashid18a.pdf Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class QMIX_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/qtran_learner.py b/xuance/mindspore/learners/multi_agent_rl/qtran_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/multi_agent_rl/qtran_learner.py rename to xuance/mindspore/learners/multi_agent_rl/qtran_learner.py index 1a2f93794..66d7c3757 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/qtran_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/qtran_learner.py @@ -4,7 +4,7 @@ http://proceedings.mlr.press/v97/son19a/son19a.pdf Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class QTRAN_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/vdac_learner.py b/xuance/mindspore/learners/multi_agent_rl/vdac_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/multi_agent_rl/vdac_learner.py rename to xuance/mindspore/learners/multi_agent_rl/vdac_learner.py index 523bc2105..7f101a566 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/vdac_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/vdac_learner.py @@ -3,7 +3,7 @@ Paper link: https://ojs.aaai.org/index.php/AAAI/article/view/17353 Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class VDAC_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/vdn_learner.py b/xuance/mindspore/learners/multi_agent_rl/vdn_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/multi_agent_rl/vdn_learner.py rename to xuance/mindspore/learners/multi_agent_rl/vdn_learner.py index e7593c713..7114bcfb3 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/vdn_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/vdn_learner.py @@ -4,7 +4,7 @@ https://arxiv.org/pdf/1706.05296.pdf Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class VDN_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/multi_agent_rl/wqmix_learner.py b/xuance/mindspore/learners/multi_agent_rl/wqmix_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/multi_agent_rl/wqmix_learner.py rename to xuance/mindspore/learners/multi_agent_rl/wqmix_learner.py index 753b94434..2008a93f5 100644 --- a/xuanpolicy/mindspore/learners/multi_agent_rl/wqmix_learner.py +++ b/xuance/mindspore/learners/multi_agent_rl/wqmix_learner.py @@ -4,7 +4,7 @@ https://proceedings.neurips.cc/paper/2020/file/73a427badebe0e32caa2e1fc7530b7f3-Paper.pdf Implementation: MindSpore """ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class WQMIX_Learner(LearnerMAS): diff --git a/xuanpolicy/mindspore/learners/policy_gradient/__init__.py b/xuance/mindspore/learners/policy_gradient/__init__.py similarity index 100% rename from xuanpolicy/mindspore/learners/policy_gradient/__init__.py rename to xuance/mindspore/learners/policy_gradient/__init__.py diff --git a/xuanpolicy/mindspore/learners/policy_gradient/a2c_learner.py b/xuance/mindspore/learners/policy_gradient/a2c_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/policy_gradient/a2c_learner.py rename to xuance/mindspore/learners/policy_gradient/a2c_learner.py index 66751df29..d9c0600dc 100644 --- a/xuanpolicy/mindspore/learners/policy_gradient/a2c_learner.py +++ b/xuance/mindspore/learners/policy_gradient/a2c_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class A2C_Learner(Learner): diff --git a/xuanpolicy/mindspore/learners/policy_gradient/ddpg_learner.py b/xuance/mindspore/learners/policy_gradient/ddpg_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/policy_gradient/ddpg_learner.py rename to xuance/mindspore/learners/policy_gradient/ddpg_learner.py index 8063c2fa7..4707328b5 100644 --- a/xuanpolicy/mindspore/learners/policy_gradient/ddpg_learner.py +++ b/xuance/mindspore/learners/policy_gradient/ddpg_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class DDPG_Learner(Learner): diff --git a/xuanpolicy/mindspore/learners/policy_gradient/mpdqn_learner.py b/xuance/mindspore/learners/policy_gradient/mpdqn_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/policy_gradient/mpdqn_learner.py rename to xuance/mindspore/learners/policy_gradient/mpdqn_learner.py index 35fe28f40..c0629a092 100644 --- a/xuanpolicy/mindspore/learners/policy_gradient/mpdqn_learner.py +++ b/xuance/mindspore/learners/policy_gradient/mpdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.ops import OneHot diff --git a/xuanpolicy/mindspore/learners/policy_gradient/pdqn_learner.py b/xuance/mindspore/learners/policy_gradient/pdqn_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/policy_gradient/pdqn_learner.py rename to xuance/mindspore/learners/policy_gradient/pdqn_learner.py index 41c6cc45a..14a6416b2 100644 --- a/xuanpolicy/mindspore/learners/policy_gradient/pdqn_learner.py +++ b/xuance/mindspore/learners/policy_gradient/pdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.ops import OneHot diff --git a/xuanpolicy/mindspore/learners/policy_gradient/pg_learner.py b/xuance/mindspore/learners/policy_gradient/pg_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/policy_gradient/pg_learner.py rename to xuance/mindspore/learners/policy_gradient/pg_learner.py index 7d9b6be8e..7d3086a92 100644 --- a/xuanpolicy/mindspore/learners/policy_gradient/pg_learner.py +++ b/xuance/mindspore/learners/policy_gradient/pg_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class PG_Learner(Learner): diff --git a/xuanpolicy/mindspore/learners/policy_gradient/ppg_learner.py b/xuance/mindspore/learners/policy_gradient/ppg_learner.py similarity index 97% rename from xuanpolicy/mindspore/learners/policy_gradient/ppg_learner.py rename to xuance/mindspore/learners/policy_gradient/ppg_learner.py index 9dad265f4..28717e509 100644 --- a/xuanpolicy/mindspore/learners/policy_gradient/ppg_learner.py +++ b/xuance/mindspore/learners/policy_gradient/ppg_learner.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.learners import * -from xuanpolicy.mindspore.utils.operations import merge_distributions +from xuance.mindspore.learners import * +from xuance.mindspore.utils.operations import merge_distributions from mindspore.nn.probability.distribution import Categorical class PPG_Learner(Learner): diff --git a/xuanpolicy/mindspore/learners/policy_gradient/ppoclip_learner.py b/xuance/mindspore/learners/policy_gradient/ppoclip_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/policy_gradient/ppoclip_learner.py rename to xuance/mindspore/learners/policy_gradient/ppoclip_learner.py index f10c5575f..d367de310 100644 --- a/xuanpolicy/mindspore/learners/policy_gradient/ppoclip_learner.py +++ b/xuance/mindspore/learners/policy_gradient/ppoclip_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class PPOCLIP_Learner(Learner): diff --git a/xuanpolicy/mindspore/learners/policy_gradient/ppokl_learner.py b/xuance/mindspore/learners/policy_gradient/ppokl_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/policy_gradient/ppokl_learner.py rename to xuance/mindspore/learners/policy_gradient/ppokl_learner.py index a4a3e83ee..91ef89759 100644 --- a/xuanpolicy/mindspore/learners/policy_gradient/ppokl_learner.py +++ b/xuance/mindspore/learners/policy_gradient/ppokl_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class PPOCLIP_Learner(Learner): diff --git a/xuanpolicy/mindspore/learners/policy_gradient/sac_learner.py b/xuance/mindspore/learners/policy_gradient/sac_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/policy_gradient/sac_learner.py rename to xuance/mindspore/learners/policy_gradient/sac_learner.py index 2ef055b5b..d9c716c4b 100644 --- a/xuanpolicy/mindspore/learners/policy_gradient/sac_learner.py +++ b/xuance/mindspore/learners/policy_gradient/sac_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.nn.probability.distribution import Normal diff --git a/xuanpolicy/mindspore/learners/policy_gradient/sacdis_learner.py b/xuance/mindspore/learners/policy_gradient/sacdis_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/policy_gradient/sacdis_learner.py rename to xuance/mindspore/learners/policy_gradient/sacdis_learner.py index 6b982a3e6..eb20cd7ce 100644 --- a/xuanpolicy/mindspore/learners/policy_gradient/sacdis_learner.py +++ b/xuance/mindspore/learners/policy_gradient/sacdis_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class SACDIS_Learner(Learner): diff --git a/xuanpolicy/mindspore/learners/policy_gradient/spdqn_learner.py b/xuance/mindspore/learners/policy_gradient/spdqn_learner.py similarity index 99% rename from xuanpolicy/mindspore/learners/policy_gradient/spdqn_learner.py rename to xuance/mindspore/learners/policy_gradient/spdqn_learner.py index f08fa52b1..aaeb74706 100644 --- a/xuanpolicy/mindspore/learners/policy_gradient/spdqn_learner.py +++ b/xuance/mindspore/learners/policy_gradient/spdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.ops import OneHot diff --git a/xuanpolicy/mindspore/learners/policy_gradient/td3_learner.py b/xuance/mindspore/learners/policy_gradient/td3_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/policy_gradient/td3_learner.py rename to xuance/mindspore/learners/policy_gradient/td3_learner.py index 70d4631d0..3f5bd98e2 100644 --- a/xuanpolicy/mindspore/learners/policy_gradient/td3_learner.py +++ b/xuance/mindspore/learners/policy_gradient/td3_learner.py @@ -2,7 +2,7 @@ # 1. noisy action in target actor # 2. double critic network # 3. delayed actor update -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * class TD3_Learner(Learner): diff --git a/xuanpolicy/mindspore/learners/qlearning_family/__init__.py b/xuance/mindspore/learners/qlearning_family/__init__.py similarity index 100% rename from xuanpolicy/mindspore/learners/qlearning_family/__init__.py rename to xuance/mindspore/learners/qlearning_family/__init__.py diff --git a/xuanpolicy/mindspore/learners/qlearning_family/c51_learner.py b/xuance/mindspore/learners/qlearning_family/c51_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/qlearning_family/c51_learner.py rename to xuance/mindspore/learners/qlearning_family/c51_learner.py index c2697d426..4ff6cd23c 100644 --- a/xuanpolicy/mindspore/learners/qlearning_family/c51_learner.py +++ b/xuance/mindspore/learners/qlearning_family/c51_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.ops import OneHot,Log,BatchMatMul,ExpandDims,Squeeze,ReduceSum,Abs,ReduceMean,clip_by_value diff --git a/xuanpolicy/mindspore/learners/qlearning_family/cdqn_learner.py b/xuance/mindspore/learners/qlearning_family/cdqn_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/qlearning_family/cdqn_learner.py rename to xuance/mindspore/learners/qlearning_family/cdqn_learner.py index a44cd1184..d090eac17 100644 --- a/xuanpolicy/mindspore/learners/qlearning_family/cdqn_learner.py +++ b/xuance/mindspore/learners/qlearning_family/cdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.ops import OneHot diff --git a/xuanpolicy/mindspore/learners/qlearning_family/cldqn_learner.py b/xuance/mindspore/learners/qlearning_family/cldqn_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/qlearning_family/cldqn_learner.py rename to xuance/mindspore/learners/qlearning_family/cldqn_learner.py index 10848476a..dce09aee8 100644 --- a/xuanpolicy/mindspore/learners/qlearning_family/cldqn_learner.py +++ b/xuance/mindspore/learners/qlearning_family/cldqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.ops import OneHot diff --git a/xuanpolicy/mindspore/learners/qlearning_family/ddqn_learner.py b/xuance/mindspore/learners/qlearning_family/ddqn_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/qlearning_family/ddqn_learner.py rename to xuance/mindspore/learners/qlearning_family/ddqn_learner.py index 82955e49d..149efaf57 100644 --- a/xuanpolicy/mindspore/learners/qlearning_family/ddqn_learner.py +++ b/xuance/mindspore/learners/qlearning_family/ddqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.ops import OneHot diff --git a/xuanpolicy/mindspore/learners/qlearning_family/dqn_learner.py b/xuance/mindspore/learners/qlearning_family/dqn_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/qlearning_family/dqn_learner.py rename to xuance/mindspore/learners/qlearning_family/dqn_learner.py index fe394f99f..af29f9d5d 100644 --- a/xuanpolicy/mindspore/learners/qlearning_family/dqn_learner.py +++ b/xuance/mindspore/learners/qlearning_family/dqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.ops import OneHot diff --git a/xuanpolicy/mindspore/learners/qlearning_family/dueldqn_learner.py b/xuance/mindspore/learners/qlearning_family/dueldqn_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/qlearning_family/dueldqn_learner.py rename to xuance/mindspore/learners/qlearning_family/dueldqn_learner.py index ae374e770..81213fa13 100644 --- a/xuanpolicy/mindspore/learners/qlearning_family/dueldqn_learner.py +++ b/xuance/mindspore/learners/qlearning_family/dueldqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.ops import OneHot diff --git a/xuanpolicy/mindspore/learners/qlearning_family/ldqn_learner.py b/xuance/mindspore/learners/qlearning_family/ldqn_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/qlearning_family/ldqn_learner.py rename to xuance/mindspore/learners/qlearning_family/ldqn_learner.py index 50c897bfd..d7936f149 100644 --- a/xuanpolicy/mindspore/learners/qlearning_family/ldqn_learner.py +++ b/xuance/mindspore/learners/qlearning_family/ldqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.ops import OneHot diff --git a/xuanpolicy/mindspore/learners/qlearning_family/perdqn_learner.py b/xuance/mindspore/learners/qlearning_family/perdqn_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/qlearning_family/perdqn_learner.py rename to xuance/mindspore/learners/qlearning_family/perdqn_learner.py index e6f56ad6a..b1365a00d 100644 --- a/xuanpolicy/mindspore/learners/qlearning_family/perdqn_learner.py +++ b/xuance/mindspore/learners/qlearning_family/perdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.ops import OneHot diff --git a/xuanpolicy/mindspore/learners/qlearning_family/qrdqn_learner.py b/xuance/mindspore/learners/qlearning_family/qrdqn_learner.py similarity index 98% rename from xuanpolicy/mindspore/learners/qlearning_family/qrdqn_learner.py rename to xuance/mindspore/learners/qlearning_family/qrdqn_learner.py index e90dd80fb..782dc373f 100644 --- a/xuanpolicy/mindspore/learners/qlearning_family/qrdqn_learner.py +++ b/xuance/mindspore/learners/qlearning_family/qrdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.mindspore.learners import * +from xuance.mindspore.learners import * from mindspore.ops import OneHot,ExpandDims,ReduceSum diff --git a/xuanpolicy/mindspore/policies/__init__.py b/xuance/mindspore/policies/__init__.py similarity index 100% rename from xuanpolicy/mindspore/policies/__init__.py rename to xuance/mindspore/policies/__init__.py diff --git a/xuanpolicy/mindspore/policies/categorical.py b/xuance/mindspore/policies/categorical.py similarity index 99% rename from xuanpolicy/mindspore/policies/categorical.py rename to xuance/mindspore/policies/categorical.py index 004cdccb6..cbf9b5659 100644 --- a/xuanpolicy/mindspore/policies/categorical.py +++ b/xuance/mindspore/policies/categorical.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.policies import * -from xuanpolicy.mindspore.utils import * +from xuance.mindspore.policies import * +from xuance.mindspore.utils import * from mindspore.nn.probability.distribution import Categorical import copy diff --git a/xuanpolicy/mindspore/policies/categorical_marl.py b/xuance/mindspore/policies/categorical_marl.py similarity index 98% rename from xuanpolicy/mindspore/policies/categorical_marl.py rename to xuance/mindspore/policies/categorical_marl.py index 7ea17ee40..6b64acce8 100644 --- a/xuanpolicy/mindspore/policies/categorical_marl.py +++ b/xuance/mindspore/policies/categorical_marl.py @@ -1,6 +1,6 @@ -from xuanpolicy.mindspore.policies import * -from xuanpolicy.mindspore.utils import * -from xuanpolicy.mindspore.representations import Basic_Identical +from xuance.mindspore.policies import * +from xuance.mindspore.utils import * +from xuance.mindspore.representations import Basic_Identical from .deterministic_marl import BasicQhead from mindspore.nn.probability.distribution import Categorical import copy diff --git a/xuanpolicy/mindspore/policies/deterministic.py b/xuance/mindspore/policies/deterministic.py similarity index 99% rename from xuanpolicy/mindspore/policies/deterministic.py rename to xuance/mindspore/policies/deterministic.py index c6c795e49..0ac70b409 100644 --- a/xuanpolicy/mindspore/policies/deterministic.py +++ b/xuance/mindspore/policies/deterministic.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.policies import * -from xuanpolicy.mindspore.utils import * +from xuance.mindspore.policies import * +from xuance.mindspore.utils import * import copy from gym.spaces import Space, Box, Discrete, Dict diff --git a/xuanpolicy/mindspore/policies/deterministic_marl.py b/xuance/mindspore/policies/deterministic_marl.py similarity index 99% rename from xuanpolicy/mindspore/policies/deterministic_marl.py rename to xuance/mindspore/policies/deterministic_marl.py index 1be3dd30f..b38a647cf 100644 --- a/xuanpolicy/mindspore/policies/deterministic_marl.py +++ b/xuance/mindspore/policies/deterministic_marl.py @@ -1,9 +1,9 @@ import markdown.extensions.smarty -from xuanpolicy.mindspore.policies import * -from xuanpolicy.mindspore.utils import * +from xuance.mindspore.policies import * +from xuance.mindspore.utils import * import copy -from xuanpolicy.mindspore.representations import Basic_Identical +from xuance.mindspore.representations import Basic_Identical from mindspore.nn.probability.distribution import Categorical diff --git a/xuanpolicy/mindspore/policies/gaussian.py b/xuance/mindspore/policies/gaussian.py similarity index 99% rename from xuanpolicy/mindspore/policies/gaussian.py rename to xuance/mindspore/policies/gaussian.py index 340423a64..ba3600376 100644 --- a/xuanpolicy/mindspore/policies/gaussian.py +++ b/xuance/mindspore/policies/gaussian.py @@ -1,5 +1,5 @@ -from xuanpolicy.mindspore.policies import * -from xuanpolicy.mindspore.utils import * +from xuance.mindspore.policies import * +from xuance.mindspore.utils import * from mindspore.nn.probability.distribution import Normal import copy diff --git a/xuanpolicy/mindspore/policies/gaussian_marl.py b/xuance/mindspore/policies/gaussian_marl.py similarity index 98% rename from xuanpolicy/mindspore/policies/gaussian_marl.py rename to xuance/mindspore/policies/gaussian_marl.py index 4dd583d36..0fef69069 100644 --- a/xuanpolicy/mindspore/policies/gaussian_marl.py +++ b/xuance/mindspore/policies/gaussian_marl.py @@ -1,6 +1,6 @@ -from xuanpolicy.mindspore.policies import * -from xuanpolicy.mindspore.utils import * -from xuanpolicy.mindspore.representations import Basic_Identical +from xuance.mindspore.policies import * +from xuance.mindspore.utils import * +from xuance.mindspore.representations import Basic_Identical from mindspore.nn.probability.distribution import Normal import copy diff --git a/xuanpolicy/mindspore/policies/mixers.py b/xuance/mindspore/policies/mixers.py similarity index 100% rename from xuanpolicy/mindspore/policies/mixers.py rename to xuance/mindspore/policies/mixers.py diff --git a/xuanpolicy/mindspore/representations/__init__.py b/xuance/mindspore/representations/__init__.py similarity index 100% rename from xuanpolicy/mindspore/representations/__init__.py rename to xuance/mindspore/representations/__init__.py diff --git a/xuanpolicy/mindspore/representations/networks.py b/xuance/mindspore/representations/networks.py similarity index 99% rename from xuanpolicy/mindspore/representations/networks.py rename to xuance/mindspore/representations/networks.py index c4267fb9e..da5d5e21e 100644 --- a/xuanpolicy/mindspore/representations/networks.py +++ b/xuance/mindspore/representations/networks.py @@ -2,7 +2,7 @@ import mindspore.nn as nn from typing import Sequence, Optional, Union, Callable import numpy as np -from xuanpolicy.mindspore.utils.layers import ModuleType, mlp_block, cnn_block, gru_block +from xuance.mindspore.utils.layers import ModuleType, mlp_block, cnn_block, gru_block # directly returns the original observation diff --git a/xuanpolicy/mindspore/runners/__init__.py b/xuance/mindspore/runners/__init__.py similarity index 100% rename from xuanpolicy/mindspore/runners/__init__.py rename to xuance/mindspore/runners/__init__.py diff --git a/xuanpolicy/mindspore/runners/runner_basic.py b/xuance/mindspore/runners/runner_basic.py similarity index 98% rename from xuanpolicy/mindspore/runners/runner_basic.py rename to xuance/mindspore/runners/runner_basic.py index b5a78bd92..4ed0ebadc 100644 --- a/xuanpolicy/mindspore/runners/runner_basic.py +++ b/xuance/mindspore/runners/runner_basic.py @@ -1,6 +1,6 @@ import time -from xuanpolicy.environment import make_envs +from xuance.environment import make_envs class Runner_Base(object): diff --git a/xuanpolicy/mindspore/runners/runner_drl.py b/xuance/mindspore/runners/runner_drl.py similarity index 92% rename from xuanpolicy/mindspore/runners/runner_drl.py rename to xuance/mindspore/runners/runner_drl.py index 1607ebf11..a4167cb61 100644 --- a/xuanpolicy/mindspore/runners/runner_drl.py +++ b/xuance/mindspore/runners/runner_drl.py @@ -1,9 +1,9 @@ from .runner_basic import * -from xuanpolicy.mindspore.agents import get_total_iters -from xuanpolicy.mindspore.representations import REGISTRY as REGISTRY_Representation -from xuanpolicy.mindspore.agents import REGISTRY as REGISTRY_Agent -from xuanpolicy.mindspore.policies import REGISTRY as REGISTRY_Policy -from xuanpolicy.mindspore.utils.input_reformat import get_repre_in, get_policy_in +from xuance.mindspore.agents import get_total_iters +from xuance.mindspore.representations import REGISTRY as REGISTRY_Representation +from xuance.mindspore.agents import REGISTRY as REGISTRY_Agent +from xuance.mindspore.policies import REGISTRY as REGISTRY_Policy +from xuance.mindspore.utils.input_reformat import get_repre_in, get_policy_in import itertools from mindspore.nn import Adam from mindspore.nn.learning_rate_schedule import ExponentialDecayLR as lr_decay_model diff --git a/xuanpolicy/mindspore/runners/runner_marl.py b/xuance/mindspore/runners/runner_marl.py similarity index 98% rename from xuanpolicy/mindspore/runners/runner_marl.py rename to xuance/mindspore/runners/runner_marl.py index b9e0a2fe1..6e54b9d18 100644 --- a/xuanpolicy/mindspore/runners/runner_marl.py +++ b/xuance/mindspore/runners/runner_marl.py @@ -1,5 +1,5 @@ from .runner_basic import * -from xuanpolicy.mindspore.agents import REGISTRY as REGISTRY_Agent +from xuance.mindspore.agents import REGISTRY as REGISTRY_Agent from gym.spaces import Box from tqdm import tqdm import numpy as np diff --git a/xuanpolicy/mindspore/utils/__init__.py b/xuance/mindspore/utils/__init__.py similarity index 100% rename from xuanpolicy/mindspore/utils/__init__.py rename to xuance/mindspore/utils/__init__.py diff --git a/xuanpolicy/mindspore/utils/distributions.py b/xuance/mindspore/utils/distributions.py similarity index 100% rename from xuanpolicy/mindspore/utils/distributions.py rename to xuance/mindspore/utils/distributions.py diff --git a/xuanpolicy/mindspore/utils/input_reformat.py b/xuance/mindspore/utils/input_reformat.py similarity index 94% rename from xuanpolicy/mindspore/utils/input_reformat.py rename to xuance/mindspore/utils/input_reformat.py index 630e8e9e1..dc3f81c03 100644 --- a/xuanpolicy/mindspore/utils/input_reformat.py +++ b/xuance/mindspore/utils/input_reformat.py @@ -1,7 +1,7 @@ -from xuanpolicy.common import space2shape +from xuance.common import space2shape from copy import deepcopy -from xuanpolicy.mindspore.policies import Policy_Inputs, Policy_Inputs_All -from xuanpolicy.mindspore.representations import Representation_Inputs, Representation_Inputs_All +from xuance.mindspore.policies import Policy_Inputs, Policy_Inputs_All +from xuance.mindspore.representations import Representation_Inputs, Representation_Inputs_All from operator import itemgetter import mindspore.nn as nn from mindspore.common.initializer import TruncatedNormal diff --git a/xuanpolicy/mindspore/utils/layers.py b/xuance/mindspore/utils/layers.py similarity index 100% rename from xuanpolicy/mindspore/utils/layers.py rename to xuance/mindspore/utils/layers.py diff --git a/xuanpolicy/mindspore/utils/operations.py b/xuance/mindspore/utils/operations.py similarity index 100% rename from xuanpolicy/mindspore/utils/operations.py rename to xuance/mindspore/utils/operations.py diff --git a/xuanpolicy/mindspore/utils/set_trainer.py b/xuance/mindspore/utils/set_trainer.py similarity index 100% rename from xuanpolicy/mindspore/utils/set_trainer.py rename to xuance/mindspore/utils/set_trainer.py diff --git a/xuanpolicy/tensorflow/__init__.py b/xuance/tensorflow/__init__.py similarity index 100% rename from xuanpolicy/tensorflow/__init__.py rename to xuance/tensorflow/__init__.py diff --git a/xuanpolicy/tensorflow/agents/__init__.py b/xuance/tensorflow/agents/__init__.py similarity index 87% rename from xuanpolicy/tensorflow/agents/__init__.py rename to xuance/tensorflow/agents/__init__.py index 347d51d5a..74e6e8c1d 100644 --- a/xuanpolicy/tensorflow/agents/__init__.py +++ b/xuance/tensorflow/agents/__init__.py @@ -9,15 +9,15 @@ import tensorflow as tf import tensorflow.keras as tk -from xuanpolicy.environment import * -from xuanpolicy.common import * -from xuanpolicy.tensorflow.learners import * -from xuanpolicy.tensorflow.policies import * -from xuanpolicy.tensorflow.utils import * -from xuanpolicy.tensorflow.policies import REGISTRY as REGISTRY_Policy -from xuanpolicy.tensorflow.utils.input_reformat import get_repre_in, get_policy_in_marl -from xuanpolicy.tensorflow.representations import REGISTRY as REGISTRY_Representation -from xuanpolicy.tensorflow.runners.runner_basic import MyLinearLR +from xuance.environment import * +from xuance.common import * +from xuance.tensorflow.learners import * +from xuance.tensorflow.policies import * +from xuance.tensorflow.utils import * +from xuance.tensorflow.policies import REGISTRY as REGISTRY_Policy +from xuance.tensorflow.utils.input_reformat import get_repre_in, get_policy_in_marl +from xuance.tensorflow.representations import REGISTRY as REGISTRY_Representation +from xuance.tensorflow.runners.runner_basic import MyLinearLR from .agent import Agent from .agents_marl import MARLAgents, RandomAgents, get_total_iters diff --git a/xuanpolicy/tensorflow/agents/agent.py b/xuance/tensorflow/agents/agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/agent.py rename to xuance/tensorflow/agents/agent.py index 1f42c5690..70e00979d 100644 --- a/xuanpolicy/tensorflow/agents/agent.py +++ b/xuance/tensorflow/agents/agent.py @@ -1,7 +1,7 @@ import socket import time from pathlib import Path -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class Agent(ABC): diff --git a/xuanpolicy/tensorflow/agents/agents_marl.py b/xuance/tensorflow/agents/agents_marl.py similarity index 98% rename from xuanpolicy/tensorflow/agents/agents_marl.py rename to xuance/tensorflow/agents/agents_marl.py index 6381fb040..462c358a2 100644 --- a/xuanpolicy/tensorflow/agents/agents_marl.py +++ b/xuance/tensorflow/agents/agents_marl.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class MARLAgents(object): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/__init__.py b/xuance/tensorflow/agents/multi_agent_rl/__init__.py similarity index 100% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/__init__.py rename to xuance/tensorflow/agents/multi_agent_rl/__init__.py diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/coma_agents.py b/xuance/tensorflow/agents/multi_agent_rl/coma_agents.py similarity index 97% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/coma_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/coma_agents.py index 08e332709..3336054fb 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/coma_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/coma_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.tensorflow.agents import * -from xuanpolicy.tensorflow.agents.agents_marl import linear_decay_or_increase +from xuance.tensorflow.agents import * +from xuance.tensorflow.agents.agents_marl import linear_decay_or_increase class COMA_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/dcg_agents.py b/xuance/tensorflow/agents/multi_agent_rl/dcg_agents.py similarity index 97% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/dcg_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/dcg_agents.py index d1f01dd97..e774a56b5 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/dcg_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/dcg_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.tensorflow.agents import * -from xuanpolicy.tensorflow.agents.agents_marl import linear_decay_or_increase +from xuance.tensorflow.agents import * +from xuance.tensorflow.agents.agents_marl import linear_decay_or_increase class DCG_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/iddpg_agents.py b/xuance/tensorflow/agents/multi_agent_rl/iddpg_agents.py similarity index 99% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/iddpg_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/iddpg_agents.py index f486dcf7b..ec5a17a4e 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/iddpg_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/iddpg_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class IDDPG_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/iql_agents.py b/xuance/tensorflow/agents/multi_agent_rl/iql_agents.py similarity index 97% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/iql_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/iql_agents.py index d3d419450..30aa3efb9 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/iql_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/iql_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.tensorflow.agents import * -from xuanpolicy.tensorflow.agents.agents_marl import linear_decay_or_increase +from xuance.tensorflow.agents import * +from xuance.tensorflow.agents.agents_marl import linear_decay_or_increase class IQL_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/isac_agents.py b/xuance/tensorflow/agents/multi_agent_rl/isac_agents.py similarity index 99% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/isac_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/isac_agents.py index 8f83c0ff6..e0a4b32db 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/isac_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/isac_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class ISAC_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/maddpg_agents.py b/xuance/tensorflow/agents/multi_agent_rl/maddpg_agents.py similarity index 99% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/maddpg_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/maddpg_agents.py index 08f60bb0b..67d2c5c1a 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/maddpg_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/maddpg_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class MADDPG_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/mappoclip_agents.py b/xuance/tensorflow/agents/multi_agent_rl/mappoclip_agents.py similarity index 99% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/mappoclip_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/mappoclip_agents.py index 34782b771..3865b81a4 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/mappoclip_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/mappoclip_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class MAPPO_Clip_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/mappokl_agents.py b/xuance/tensorflow/agents/multi_agent_rl/mappokl_agents.py similarity index 99% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/mappokl_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/mappokl_agents.py index 166b3cd95..21c696e6b 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/mappokl_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/mappokl_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class MAPPO_KL_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/masac_agents.py b/xuance/tensorflow/agents/multi_agent_rl/masac_agents.py similarity index 99% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/masac_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/masac_agents.py index 0f14bb038..c769d17e3 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/masac_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/masac_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class MASAC_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/matd3_agents.py b/xuance/tensorflow/agents/multi_agent_rl/matd3_agents.py similarity index 99% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/matd3_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/matd3_agents.py index 0360793c2..1a2aba94c 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/matd3_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/matd3_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class MATD3_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/mfac_agents.py b/xuance/tensorflow/agents/multi_agent_rl/mfac_agents.py similarity index 99% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/mfac_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/mfac_agents.py index 6575b008f..83e6e50d6 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/mfac_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/mfac_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class MFAC_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/mfq_agents.py b/xuance/tensorflow/agents/multi_agent_rl/mfq_agents.py similarity index 97% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/mfq_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/mfq_agents.py index 21571b2f4..bf3d04bc6 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/mfq_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/mfq_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.tensorflow.agents import * -from xuanpolicy.tensorflow.agents.agents_marl import linear_decay_or_increase +from xuance.tensorflow.agents import * +from xuance.tensorflow.agents.agents_marl import linear_decay_or_increase class MFQ_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/qmix_agents.py b/xuance/tensorflow/agents/multi_agent_rl/qmix_agents.py similarity index 97% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/qmix_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/qmix_agents.py index abbcc565c..c18fa26d8 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/qmix_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/qmix_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.tensorflow.agents import * -from xuanpolicy.tensorflow.agents.agents_marl import linear_decay_or_increase +from xuance.tensorflow.agents import * +from xuance.tensorflow.agents.agents_marl import linear_decay_or_increase class QMIX_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/qtran_agents.py b/xuance/tensorflow/agents/multi_agent_rl/qtran_agents.py similarity index 97% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/qtran_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/qtran_agents.py index 63d1ebf59..89b21f6a8 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/qtran_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/qtran_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.tensorflow.agents import * -from xuanpolicy.tensorflow.agents.agents_marl import linear_decay_or_increase +from xuance.tensorflow.agents import * +from xuance.tensorflow.agents.agents_marl import linear_decay_or_increase class QTRAN_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/vdac_agents.py b/xuance/tensorflow/agents/multi_agent_rl/vdac_agents.py similarity index 99% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/vdac_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/vdac_agents.py index b5e898a2c..3a7515653 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/vdac_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/vdac_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class VDAC_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/vdn_agents.py b/xuance/tensorflow/agents/multi_agent_rl/vdn_agents.py similarity index 97% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/vdn_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/vdn_agents.py index 658ba407c..9df1ba4c9 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/vdn_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/vdn_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.tensorflow.agents import * -from xuanpolicy.tensorflow.agents.agents_marl import linear_decay_or_increase +from xuance.tensorflow.agents import * +from xuance.tensorflow.agents.agents_marl import linear_decay_or_increase class VDN_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/multi_agent_rl/wqmix_agents.py b/xuance/tensorflow/agents/multi_agent_rl/wqmix_agents.py similarity index 97% rename from xuanpolicy/tensorflow/agents/multi_agent_rl/wqmix_agents.py rename to xuance/tensorflow/agents/multi_agent_rl/wqmix_agents.py index 2f80733e0..6ac253434 100644 --- a/xuanpolicy/tensorflow/agents/multi_agent_rl/wqmix_agents.py +++ b/xuance/tensorflow/agents/multi_agent_rl/wqmix_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.tensorflow.agents import * -from xuanpolicy.tensorflow.agents.agents_marl import linear_decay_or_increase +from xuance.tensorflow.agents import * +from xuance.tensorflow.agents.agents_marl import linear_decay_or_increase class WQMIX_Agents(MARLAgents): diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/__init__.py b/xuance/tensorflow/agents/policy_gradient/__init__.py similarity index 100% rename from xuanpolicy/tensorflow/agents/policy_gradient/__init__.py rename to xuance/tensorflow/agents/policy_gradient/__init__.py diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/a2c_agent.py b/xuance/tensorflow/agents/policy_gradient/a2c_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/policy_gradient/a2c_agent.py rename to xuance/tensorflow/agents/policy_gradient/a2c_agent.py index 1cf900726..f2fefa93f 100644 --- a/xuanpolicy/tensorflow/agents/policy_gradient/a2c_agent.py +++ b/xuance/tensorflow/agents/policy_gradient/a2c_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class A2C_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/ddpg_agent.py b/xuance/tensorflow/agents/policy_gradient/ddpg_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/policy_gradient/ddpg_agent.py rename to xuance/tensorflow/agents/policy_gradient/ddpg_agent.py index bfa88f033..b32e6d3bc 100644 --- a/xuanpolicy/tensorflow/agents/policy_gradient/ddpg_agent.py +++ b/xuance/tensorflow/agents/policy_gradient/ddpg_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class DDPG_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/mpdqn_agent.py b/xuance/tensorflow/agents/policy_gradient/mpdqn_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/policy_gradient/mpdqn_agent.py rename to xuance/tensorflow/agents/policy_gradient/mpdqn_agent.py index 07da77013..672d7117b 100644 --- a/xuanpolicy/tensorflow/agents/policy_gradient/mpdqn_agent.py +++ b/xuance/tensorflow/agents/policy_gradient/mpdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * import gym from gym import spaces diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/pdqn_agent.py b/xuance/tensorflow/agents/policy_gradient/pdqn_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/policy_gradient/pdqn_agent.py rename to xuance/tensorflow/agents/policy_gradient/pdqn_agent.py index c265aa10c..1190c2c30 100644 --- a/xuanpolicy/tensorflow/agents/policy_gradient/pdqn_agent.py +++ b/xuance/tensorflow/agents/policy_gradient/pdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * import gym from gym import spaces diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/pg_agent.py b/xuance/tensorflow/agents/policy_gradient/pg_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/policy_gradient/pg_agent.py rename to xuance/tensorflow/agents/policy_gradient/pg_agent.py index 2bdd65ccb..a274cf53e 100644 --- a/xuanpolicy/tensorflow/agents/policy_gradient/pg_agent.py +++ b/xuance/tensorflow/agents/policy_gradient/pg_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class PG_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/ppg_agent.py b/xuance/tensorflow/agents/policy_gradient/ppg_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/policy_gradient/ppg_agent.py rename to xuance/tensorflow/agents/policy_gradient/ppg_agent.py index 0f966882b..da16d3181 100644 --- a/xuanpolicy/tensorflow/agents/policy_gradient/ppg_agent.py +++ b/xuance/tensorflow/agents/policy_gradient/ppg_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class PPG_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/ppoclip_agent.py b/xuance/tensorflow/agents/policy_gradient/ppoclip_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/policy_gradient/ppoclip_agent.py rename to xuance/tensorflow/agents/policy_gradient/ppoclip_agent.py index e7e857467..1ff079737 100644 --- a/xuanpolicy/tensorflow/agents/policy_gradient/ppoclip_agent.py +++ b/xuance/tensorflow/agents/policy_gradient/ppoclip_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class PPOCLIP_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/ppokl_agent.py b/xuance/tensorflow/agents/policy_gradient/ppokl_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/policy_gradient/ppokl_agent.py rename to xuance/tensorflow/agents/policy_gradient/ppokl_agent.py index 5e10bc1fa..0eb4e29e3 100644 --- a/xuanpolicy/tensorflow/agents/policy_gradient/ppokl_agent.py +++ b/xuance/tensorflow/agents/policy_gradient/ppokl_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class PPOKL_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/sac_agent.py b/xuance/tensorflow/agents/policy_gradient/sac_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/policy_gradient/sac_agent.py rename to xuance/tensorflow/agents/policy_gradient/sac_agent.py index f87f4c3dc..bf2b624b4 100644 --- a/xuanpolicy/tensorflow/agents/policy_gradient/sac_agent.py +++ b/xuance/tensorflow/agents/policy_gradient/sac_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class SAC_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/sacdis_agent.py b/xuance/tensorflow/agents/policy_gradient/sacdis_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/policy_gradient/sacdis_agent.py rename to xuance/tensorflow/agents/policy_gradient/sacdis_agent.py index 485233265..366f40da8 100644 --- a/xuanpolicy/tensorflow/agents/policy_gradient/sacdis_agent.py +++ b/xuance/tensorflow/agents/policy_gradient/sacdis_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class SACDIS_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/spdqn_agent.py b/xuance/tensorflow/agents/policy_gradient/spdqn_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/policy_gradient/spdqn_agent.py rename to xuance/tensorflow/agents/policy_gradient/spdqn_agent.py index 70c1100ea..8108f48d8 100644 --- a/xuanpolicy/tensorflow/agents/policy_gradient/spdqn_agent.py +++ b/xuance/tensorflow/agents/policy_gradient/spdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * import gym from gym import spaces diff --git a/xuanpolicy/tensorflow/agents/policy_gradient/td3_agent.py b/xuance/tensorflow/agents/policy_gradient/td3_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/policy_gradient/td3_agent.py rename to xuance/tensorflow/agents/policy_gradient/td3_agent.py index e96446de5..b165e7dc7 100644 --- a/xuanpolicy/tensorflow/agents/policy_gradient/td3_agent.py +++ b/xuance/tensorflow/agents/policy_gradient/td3_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class TD3_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/qlearning_family/__init__.py b/xuance/tensorflow/agents/qlearning_family/__init__.py similarity index 100% rename from xuanpolicy/tensorflow/agents/qlearning_family/__init__.py rename to xuance/tensorflow/agents/qlearning_family/__init__.py diff --git a/xuanpolicy/tensorflow/agents/qlearning_family/c51_agent.py b/xuance/tensorflow/agents/qlearning_family/c51_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/qlearning_family/c51_agent.py rename to xuance/tensorflow/agents/qlearning_family/c51_agent.py index aeb2d9101..ea31738fc 100644 --- a/xuanpolicy/tensorflow/agents/qlearning_family/c51_agent.py +++ b/xuance/tensorflow/agents/qlearning_family/c51_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class C51_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/qlearning_family/ddqn_agent.py b/xuance/tensorflow/agents/qlearning_family/ddqn_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/qlearning_family/ddqn_agent.py rename to xuance/tensorflow/agents/qlearning_family/ddqn_agent.py index 97b9299fa..e792e1c2d 100644 --- a/xuanpolicy/tensorflow/agents/qlearning_family/ddqn_agent.py +++ b/xuance/tensorflow/agents/qlearning_family/ddqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class DDQN_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/qlearning_family/dqn_agent.py b/xuance/tensorflow/agents/qlearning_family/dqn_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/qlearning_family/dqn_agent.py rename to xuance/tensorflow/agents/qlearning_family/dqn_agent.py index 04231c919..13f954b36 100644 --- a/xuanpolicy/tensorflow/agents/qlearning_family/dqn_agent.py +++ b/xuance/tensorflow/agents/qlearning_family/dqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class DQN_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/qlearning_family/drqn_agent.py b/xuance/tensorflow/agents/qlearning_family/drqn_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/qlearning_family/drqn_agent.py rename to xuance/tensorflow/agents/qlearning_family/drqn_agent.py index f2e73d1d3..9a6131415 100644 --- a/xuanpolicy/tensorflow/agents/qlearning_family/drqn_agent.py +++ b/xuance/tensorflow/agents/qlearning_family/drqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class DRQN_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/qlearning_family/dueldqn_agent.py b/xuance/tensorflow/agents/qlearning_family/dueldqn_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/qlearning_family/dueldqn_agent.py rename to xuance/tensorflow/agents/qlearning_family/dueldqn_agent.py index 2acfc58cf..18dfcf37c 100644 --- a/xuanpolicy/tensorflow/agents/qlearning_family/dueldqn_agent.py +++ b/xuance/tensorflow/agents/qlearning_family/dueldqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class DuelDQN_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/qlearning_family/noisydqn_agent.py b/xuance/tensorflow/agents/qlearning_family/noisydqn_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/qlearning_family/noisydqn_agent.py rename to xuance/tensorflow/agents/qlearning_family/noisydqn_agent.py index d310b0b9e..09cdd486d 100644 --- a/xuanpolicy/tensorflow/agents/qlearning_family/noisydqn_agent.py +++ b/xuance/tensorflow/agents/qlearning_family/noisydqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class NoisyDQN_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/qlearning_family/perdqn_agent.py b/xuance/tensorflow/agents/qlearning_family/perdqn_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/qlearning_family/perdqn_agent.py rename to xuance/tensorflow/agents/qlearning_family/perdqn_agent.py index abde20877..9872911ee 100644 --- a/xuanpolicy/tensorflow/agents/qlearning_family/perdqn_agent.py +++ b/xuance/tensorflow/agents/qlearning_family/perdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class PerDQN_Agent(Agent): diff --git a/xuanpolicy/tensorflow/agents/qlearning_family/qrdqn_agent.py b/xuance/tensorflow/agents/qlearning_family/qrdqn_agent.py similarity index 99% rename from xuanpolicy/tensorflow/agents/qlearning_family/qrdqn_agent.py rename to xuance/tensorflow/agents/qlearning_family/qrdqn_agent.py index 32f91e26e..c71009864 100644 --- a/xuanpolicy/tensorflow/agents/qlearning_family/qrdqn_agent.py +++ b/xuance/tensorflow/agents/qlearning_family/qrdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.agents import * +from xuance.tensorflow.agents import * class QRDQN_Agent(Agent): diff --git a/xuanpolicy/tensorflow/learners/__init__.py b/xuance/tensorflow/learners/__init__.py similarity index 100% rename from xuanpolicy/tensorflow/learners/__init__.py rename to xuance/tensorflow/learners/__init__.py diff --git a/xuanpolicy/tensorflow/learners/learner.py b/xuance/tensorflow/learners/learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/learner.py rename to xuance/tensorflow/learners/learner.py index d1763b914..176cdfbe5 100644 --- a/xuanpolicy/tensorflow/learners/learner.py +++ b/xuance/tensorflow/learners/learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * from argparse import Namespace diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/__init__.py b/xuance/tensorflow/learners/multi_agent_rl/__init__.py similarity index 100% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/__init__.py rename to xuance/tensorflow/learners/multi_agent_rl/__init__.py diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/coma_learner.py b/xuance/tensorflow/learners/multi_agent_rl/coma_learner.py similarity index 99% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/coma_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/coma_learner.py index 6540f894a..70bfa50cd 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/coma_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/coma_learner.py @@ -3,7 +3,7 @@ Paper link: https://ojs.aaai.org/index.php/AAAI/article/view/11794 Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class COMA_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/dcg_learner.py b/xuance/tensorflow/learners/multi_agent_rl/dcg_learner.py similarity index 99% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/dcg_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/dcg_learner.py index ec8c81c65..be43bad8f 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/dcg_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/dcg_learner.py @@ -5,7 +5,7 @@ """ import torch -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * import torch_scatter diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/iddpg_learner.py b/xuance/tensorflow/learners/multi_agent_rl/iddpg_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/iddpg_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/iddpg_learner.py index 796794fdd..27bff1fa7 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/iddpg_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/iddpg_learner.py @@ -2,7 +2,7 @@ Independent Deep Deterministic Policy Gradient (IDDPG) Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class IDDPG_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/iql_learner.py b/xuance/tensorflow/learners/multi_agent_rl/iql_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/iql_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/iql_learner.py index 8b4685cd1..9b250263c 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/iql_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/iql_learner.py @@ -2,7 +2,7 @@ Independent Q-learning (IQL) Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class IQL_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/isac_learner.py b/xuance/tensorflow/learners/multi_agent_rl/isac_learner.py similarity index 99% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/isac_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/isac_learner.py index 1fea0c84d..406db50d0 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/isac_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/isac_learner.py @@ -2,7 +2,7 @@ Independent Soft Actor-critic (ISAC) Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class ISAC_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/maddpg_learner.py b/xuance/tensorflow/learners/multi_agent_rl/maddpg_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/maddpg_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/maddpg_learner.py index 697029211..ce449dd9c 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/maddpg_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/maddpg_learner.py @@ -5,7 +5,7 @@ Implementation: TensorFlow 2.X Trick: Parameter sharing for all agents, with agents' one-hot IDs as actor-critic's inputs. """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class MADDPG_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/mappoclip_learner.py b/xuance/tensorflow/learners/multi_agent_rl/mappoclip_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/mappoclip_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/mappoclip_learner.py index 33ae9db39..02982d321 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/mappoclip_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/mappoclip_learner.py @@ -4,7 +4,7 @@ https://arxiv.org/pdf/2103.01955.pdf Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class MAPPO_Clip_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/mappokl_learner.py b/xuance/tensorflow/learners/multi_agent_rl/mappokl_learner.py similarity index 97% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/mappokl_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/mappokl_learner.py index 9aa4cb60a..043561fe0 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/mappokl_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/mappokl_learner.py @@ -4,8 +4,8 @@ https://arxiv.org/pdf/2103.01955.pdf Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * -from xuanpolicy.tensorflow.utils.operations import merge_distributions +from xuance.tensorflow.learners import * +from xuance.tensorflow.utils.operations import merge_distributions class MAPPO_KL_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/masac_learner.py b/xuance/tensorflow/learners/multi_agent_rl/masac_learner.py similarity index 99% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/masac_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/masac_learner.py index 3853c7f5c..29b91394f 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/masac_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/masac_learner.py @@ -2,7 +2,7 @@ Multi-agent Soft Actor-critic (MASAC) Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class MASAC_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/matd3_learner.py b/xuance/tensorflow/learners/multi_agent_rl/matd3_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/matd3_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/matd3_learner.py index e3890e5c6..c93f3bb5d 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/matd3_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/matd3_learner.py @@ -2,7 +2,7 @@ Multi-Agent TD3 """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class MATD3_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/mfac_learner.py b/xuance/tensorflow/learners/multi_agent_rl/mfac_learner.py similarity index 99% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/mfac_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/mfac_learner.py index 94df575a2..57bade1e8 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/mfac_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/mfac_learner.py @@ -4,7 +4,7 @@ http://proceedings.mlr.press/v80/yang18d/yang18d.pdf Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class MFAC_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/mfq_learner.py b/xuance/tensorflow/learners/multi_agent_rl/mfq_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/mfq_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/mfq_learner.py index 7e9657df9..9ec5aca63 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/mfq_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/mfq_learner.py @@ -4,7 +4,7 @@ http://proceedings.mlr.press/v80/yang18d/yang18d.pdf Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class MFQ_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/qmix_learner.py b/xuance/tensorflow/learners/multi_agent_rl/qmix_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/qmix_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/qmix_learner.py index afabbacff..bb135b881 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/qmix_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/qmix_learner.py @@ -4,7 +4,7 @@ http://proceedings.mlr.press/v80/rashid18a/rashid18a.pdf Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class QMIX_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/qtran_learner.py b/xuance/tensorflow/learners/multi_agent_rl/qtran_learner.py similarity index 99% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/qtran_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/qtran_learner.py index 4de88a8d3..2a76d8c3e 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/qtran_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/qtran_learner.py @@ -4,7 +4,7 @@ http://proceedings.mlr.press/v97/son19a/son19a.pdf Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class QTRAN_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/vdac_learner.py b/xuance/tensorflow/learners/multi_agent_rl/vdac_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/vdac_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/vdac_learner.py index a26fd35c5..730001d03 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/vdac_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/vdac_learner.py @@ -3,7 +3,7 @@ Paper link: https://ojs.aaai.org/index.php/AAAI/article/view/17353 Implementation: Pytorch """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class VDAC_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/vdn_learner.py b/xuance/tensorflow/learners/multi_agent_rl/vdn_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/vdn_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/vdn_learner.py index 279a3498e..dc9375020 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/vdn_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/vdn_learner.py @@ -4,7 +4,7 @@ https://arxiv.org/pdf/1706.05296.pdf Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class VDN_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/multi_agent_rl/wqmix_learner.py b/xuance/tensorflow/learners/multi_agent_rl/wqmix_learner.py similarity index 99% rename from xuanpolicy/tensorflow/learners/multi_agent_rl/wqmix_learner.py rename to xuance/tensorflow/learners/multi_agent_rl/wqmix_learner.py index 913ff45ce..49038085e 100644 --- a/xuanpolicy/tensorflow/learners/multi_agent_rl/wqmix_learner.py +++ b/xuance/tensorflow/learners/multi_agent_rl/wqmix_learner.py @@ -4,7 +4,7 @@ https://proceedings.neurips.cc/paper/2020/file/73a427badebe0e32caa2e1fc7530b7f3-Paper.pdf Implementation: TensorFlow 2.X """ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class WQMIX_Learner(LearnerMAS): diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/__init__.py b/xuance/tensorflow/learners/policy_gradient/__init__.py similarity index 100% rename from xuanpolicy/tensorflow/learners/policy_gradient/__init__.py rename to xuance/tensorflow/learners/policy_gradient/__init__.py diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/a2c_learner.py b/xuance/tensorflow/learners/policy_gradient/a2c_learner.py similarity index 97% rename from xuanpolicy/tensorflow/learners/policy_gradient/a2c_learner.py rename to xuance/tensorflow/learners/policy_gradient/a2c_learner.py index bad79ecb5..6e9ab6a7b 100644 --- a/xuanpolicy/tensorflow/learners/policy_gradient/a2c_learner.py +++ b/xuance/tensorflow/learners/policy_gradient/a2c_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class A2C_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/ddpg_learner.py b/xuance/tensorflow/learners/policy_gradient/ddpg_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/policy_gradient/ddpg_learner.py rename to xuance/tensorflow/learners/policy_gradient/ddpg_learner.py index 3820199d8..917698ee6 100644 --- a/xuanpolicy/tensorflow/learners/policy_gradient/ddpg_learner.py +++ b/xuance/tensorflow/learners/policy_gradient/ddpg_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class DDPG_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/mpdqn_learner.py b/xuance/tensorflow/learners/policy_gradient/mpdqn_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/policy_gradient/mpdqn_learner.py rename to xuance/tensorflow/learners/policy_gradient/mpdqn_learner.py index a87638420..c261b7c8c 100644 --- a/xuanpolicy/tensorflow/learners/policy_gradient/mpdqn_learner.py +++ b/xuance/tensorflow/learners/policy_gradient/mpdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class MPDQN_Learner(Learner): def __init__(self, diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/pdqn_learner.py b/xuance/tensorflow/learners/policy_gradient/pdqn_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/policy_gradient/pdqn_learner.py rename to xuance/tensorflow/learners/policy_gradient/pdqn_learner.py index 789165f94..477da7326 100644 --- a/xuanpolicy/tensorflow/learners/policy_gradient/pdqn_learner.py +++ b/xuance/tensorflow/learners/policy_gradient/pdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class PDQN_Learner(Learner): def __init__(self, diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/pg_learner.py b/xuance/tensorflow/learners/policy_gradient/pg_learner.py similarity index 97% rename from xuanpolicy/tensorflow/learners/policy_gradient/pg_learner.py rename to xuance/tensorflow/learners/policy_gradient/pg_learner.py index 2d19cf6d8..ccd05315f 100644 --- a/xuanpolicy/tensorflow/learners/policy_gradient/pg_learner.py +++ b/xuance/tensorflow/learners/policy_gradient/pg_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class PG_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/ppg_learner.py b/xuance/tensorflow/learners/policy_gradient/ppg_learner.py similarity index 97% rename from xuanpolicy/tensorflow/learners/policy_gradient/ppg_learner.py rename to xuance/tensorflow/learners/policy_gradient/ppg_learner.py index 96faa4e32..f152fe22e 100644 --- a/xuanpolicy/tensorflow/learners/policy_gradient/ppg_learner.py +++ b/xuance/tensorflow/learners/policy_gradient/ppg_learner.py @@ -1,7 +1,7 @@ from argparse import Action -from xuanpolicy.tensorflow.learners import * -from xuanpolicy.tensorflow.utils.operations import merge_distributions +from xuance.tensorflow.learners import * +from xuance.tensorflow.utils.operations import merge_distributions class PPG_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/ppoclip_learner.py b/xuance/tensorflow/learners/policy_gradient/ppoclip_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/policy_gradient/ppoclip_learner.py rename to xuance/tensorflow/learners/policy_gradient/ppoclip_learner.py index 52882a48b..2bc83df6a 100644 --- a/xuanpolicy/tensorflow/learners/policy_gradient/ppoclip_learner.py +++ b/xuance/tensorflow/learners/policy_gradient/ppoclip_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class PPOCLIP_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/ppokl_learner.py b/xuance/tensorflow/learners/policy_gradient/ppokl_learner.py similarity index 95% rename from xuanpolicy/tensorflow/learners/policy_gradient/ppokl_learner.py rename to xuance/tensorflow/learners/policy_gradient/ppokl_learner.py index 262944071..bdb4260a4 100644 --- a/xuanpolicy/tensorflow/learners/policy_gradient/ppokl_learner.py +++ b/xuance/tensorflow/learners/policy_gradient/ppokl_learner.py @@ -1,6 +1,6 @@ from torch import kl_div -from xuanpolicy.tensorflow.learners import * -from xuanpolicy.tensorflow.utils.operations import merge_distributions +from xuance.tensorflow.learners import * +from xuance.tensorflow.utils.operations import merge_distributions class PPOKL_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/sac_learner.py b/xuance/tensorflow/learners/policy_gradient/sac_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/policy_gradient/sac_learner.py rename to xuance/tensorflow/learners/policy_gradient/sac_learner.py index bca266cb7..415c06567 100644 --- a/xuanpolicy/tensorflow/learners/policy_gradient/sac_learner.py +++ b/xuance/tensorflow/learners/policy_gradient/sac_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class SAC_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/sacdis_learner.py b/xuance/tensorflow/learners/policy_gradient/sacdis_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/policy_gradient/sacdis_learner.py rename to xuance/tensorflow/learners/policy_gradient/sacdis_learner.py index b9f85bf2d..d4dfb8feb 100644 --- a/xuanpolicy/tensorflow/learners/policy_gradient/sacdis_learner.py +++ b/xuance/tensorflow/learners/policy_gradient/sacdis_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class SACDIS_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/spdqn_learner.py b/xuance/tensorflow/learners/policy_gradient/spdqn_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/policy_gradient/spdqn_learner.py rename to xuance/tensorflow/learners/policy_gradient/spdqn_learner.py index 218655ca3..a7168ee8a 100644 --- a/xuanpolicy/tensorflow/learners/policy_gradient/spdqn_learner.py +++ b/xuance/tensorflow/learners/policy_gradient/spdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class SPDQN_Learner(Learner): def __init__(self, diff --git a/xuanpolicy/tensorflow/learners/policy_gradient/td3_learner.py b/xuance/tensorflow/learners/policy_gradient/td3_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/policy_gradient/td3_learner.py rename to xuance/tensorflow/learners/policy_gradient/td3_learner.py index 786bc7508..28c6e8a28 100644 --- a/xuanpolicy/tensorflow/learners/policy_gradient/td3_learner.py +++ b/xuance/tensorflow/learners/policy_gradient/td3_learner.py @@ -2,7 +2,7 @@ # 1. noisy action in target actor # 2. double critic network # 3. delayed actor update -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class TD3_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/qlearning_family/__init__.py b/xuance/tensorflow/learners/qlearning_family/__init__.py similarity index 100% rename from xuanpolicy/tensorflow/learners/qlearning_family/__init__.py rename to xuance/tensorflow/learners/qlearning_family/__init__.py diff --git a/xuanpolicy/tensorflow/learners/qlearning_family/c51_learner.py b/xuance/tensorflow/learners/qlearning_family/c51_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/qlearning_family/c51_learner.py rename to xuance/tensorflow/learners/qlearning_family/c51_learner.py index 15ed48c85..f4481df2b 100644 --- a/xuanpolicy/tensorflow/learners/qlearning_family/c51_learner.py +++ b/xuance/tensorflow/learners/qlearning_family/c51_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class C51_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/qlearning_family/cdqn_learner.py b/xuance/tensorflow/learners/qlearning_family/cdqn_learner.py similarity index 97% rename from xuanpolicy/tensorflow/learners/qlearning_family/cdqn_learner.py rename to xuance/tensorflow/learners/qlearning_family/cdqn_learner.py index ebee3ae38..2fe3dbbce 100644 --- a/xuanpolicy/tensorflow/learners/qlearning_family/cdqn_learner.py +++ b/xuance/tensorflow/learners/qlearning_family/cdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class CDQN_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/qlearning_family/cldqn_learner.py b/xuance/tensorflow/learners/qlearning_family/cldqn_learner.py similarity index 97% rename from xuanpolicy/tensorflow/learners/qlearning_family/cldqn_learner.py rename to xuance/tensorflow/learners/qlearning_family/cldqn_learner.py index dd7e45fcf..ebefc0cbe 100644 --- a/xuanpolicy/tensorflow/learners/qlearning_family/cldqn_learner.py +++ b/xuance/tensorflow/learners/qlearning_family/cldqn_learner.py @@ -1,6 +1,6 @@ import tkinter -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class CLDQN_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/qlearning_family/ddqn_learner.py b/xuance/tensorflow/learners/qlearning_family/ddqn_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/qlearning_family/ddqn_learner.py rename to xuance/tensorflow/learners/qlearning_family/ddqn_learner.py index bd7fcea4a..19ad86002 100644 --- a/xuanpolicy/tensorflow/learners/qlearning_family/ddqn_learner.py +++ b/xuance/tensorflow/learners/qlearning_family/ddqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class DDQN_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/qlearning_family/dqn_learner.py b/xuance/tensorflow/learners/qlearning_family/dqn_learner.py similarity index 97% rename from xuanpolicy/tensorflow/learners/qlearning_family/dqn_learner.py rename to xuance/tensorflow/learners/qlearning_family/dqn_learner.py index 4a56b3c5e..2de9d76ef 100644 --- a/xuanpolicy/tensorflow/learners/qlearning_family/dqn_learner.py +++ b/xuance/tensorflow/learners/qlearning_family/dqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class DQN_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/qlearning_family/drqn_learner.py b/xuance/tensorflow/learners/qlearning_family/drqn_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/qlearning_family/drqn_learner.py rename to xuance/tensorflow/learners/qlearning_family/drqn_learner.py index 2e3887703..c71d36641 100644 --- a/xuanpolicy/tensorflow/learners/qlearning_family/drqn_learner.py +++ b/xuance/tensorflow/learners/qlearning_family/drqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class DRQN_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/qlearning_family/dueldqn_learner.py b/xuance/tensorflow/learners/qlearning_family/dueldqn_learner.py similarity index 97% rename from xuanpolicy/tensorflow/learners/qlearning_family/dueldqn_learner.py rename to xuance/tensorflow/learners/qlearning_family/dueldqn_learner.py index 44114ac16..503d3e02e 100644 --- a/xuanpolicy/tensorflow/learners/qlearning_family/dueldqn_learner.py +++ b/xuance/tensorflow/learners/qlearning_family/dueldqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class DuelDQN_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/qlearning_family/ldqn_learner.py b/xuance/tensorflow/learners/qlearning_family/ldqn_learner.py similarity index 97% rename from xuanpolicy/tensorflow/learners/qlearning_family/ldqn_learner.py rename to xuance/tensorflow/learners/qlearning_family/ldqn_learner.py index 7c7010e1d..ee2eae3dc 100644 --- a/xuanpolicy/tensorflow/learners/qlearning_family/ldqn_learner.py +++ b/xuance/tensorflow/learners/qlearning_family/ldqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class LDQN_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/qlearning_family/perdqn_learner.py b/xuance/tensorflow/learners/qlearning_family/perdqn_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/qlearning_family/perdqn_learner.py rename to xuance/tensorflow/learners/qlearning_family/perdqn_learner.py index 318405dc1..4fa29a783 100644 --- a/xuanpolicy/tensorflow/learners/qlearning_family/perdqn_learner.py +++ b/xuance/tensorflow/learners/qlearning_family/perdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class PerDQN_Learner(Learner): diff --git a/xuanpolicy/tensorflow/learners/qlearning_family/qrdqn_learner.py b/xuance/tensorflow/learners/qlearning_family/qrdqn_learner.py similarity index 98% rename from xuanpolicy/tensorflow/learners/qlearning_family/qrdqn_learner.py rename to xuance/tensorflow/learners/qlearning_family/qrdqn_learner.py index b17dadc61..bc001ce68 100644 --- a/xuanpolicy/tensorflow/learners/qlearning_family/qrdqn_learner.py +++ b/xuance/tensorflow/learners/qlearning_family/qrdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.learners import * +from xuance.tensorflow.learners import * class QRDQN_Learner(Learner): diff --git a/xuanpolicy/tensorflow/policies/__init__.py b/xuance/tensorflow/policies/__init__.py similarity index 100% rename from xuanpolicy/tensorflow/policies/__init__.py rename to xuance/tensorflow/policies/__init__.py diff --git a/xuanpolicy/tensorflow/policies/categorical.py b/xuance/tensorflow/policies/categorical.py similarity index 99% rename from xuanpolicy/tensorflow/policies/categorical.py rename to xuance/tensorflow/policies/categorical.py index bffd87dd3..db2db0d82 100644 --- a/xuanpolicy/tensorflow/policies/categorical.py +++ b/xuance/tensorflow/policies/categorical.py @@ -1,5 +1,5 @@ -from xuanpolicy.tensorflow.policies import * -from xuanpolicy.tensorflow.utils import * +from xuance.tensorflow.policies import * +from xuance.tensorflow.utils import * class ActorNet(tk.Model): diff --git a/xuanpolicy/tensorflow/policies/categorical_marl.py b/xuance/tensorflow/policies/categorical_marl.py similarity index 98% rename from xuanpolicy/tensorflow/policies/categorical_marl.py rename to xuance/tensorflow/policies/categorical_marl.py index 59b3862df..ea8c5d21c 100644 --- a/xuanpolicy/tensorflow/policies/categorical_marl.py +++ b/xuance/tensorflow/policies/categorical_marl.py @@ -1,6 +1,6 @@ -from xuanpolicy.tensorflow.policies import * -from xuanpolicy.tensorflow.utils import * -from xuanpolicy.tensorflow.representations import Basic_Identical +from xuance.tensorflow.policies import * +from xuance.tensorflow.utils import * +from xuance.tensorflow.representations import Basic_Identical from .deterministic_marl import BasicQhead diff --git a/xuanpolicy/tensorflow/policies/deterministic.py b/xuance/tensorflow/policies/deterministic.py similarity index 99% rename from xuanpolicy/tensorflow/policies/deterministic.py rename to xuance/tensorflow/policies/deterministic.py index 3bac1fd95..2ca2875a5 100644 --- a/xuanpolicy/tensorflow/policies/deterministic.py +++ b/xuance/tensorflow/policies/deterministic.py @@ -1,7 +1,7 @@ -from xuanpolicy.tensorflow.policies import * -from xuanpolicy.tensorflow.utils import * -from xuanpolicy.tensorflow.representations import Basic_Identical -from xuanpolicy.tensorflow.representations import C_DQN, L_DQN, CL_DQN +from xuance.tensorflow.policies import * +from xuance.tensorflow.utils import * +from xuance.tensorflow.representations import Basic_Identical +from xuance.tensorflow.representations import C_DQN, L_DQN, CL_DQN class BasicQhead(tk.Model): diff --git a/xuanpolicy/tensorflow/policies/deterministic_marl.py b/xuance/tensorflow/policies/deterministic_marl.py similarity index 99% rename from xuanpolicy/tensorflow/policies/deterministic_marl.py rename to xuance/tensorflow/policies/deterministic_marl.py index 9b189733c..1ed48ef73 100644 --- a/xuanpolicy/tensorflow/policies/deterministic_marl.py +++ b/xuance/tensorflow/policies/deterministic_marl.py @@ -1,6 +1,6 @@ -from xuanpolicy.tensorflow.policies import * -from xuanpolicy.tensorflow.utils import * -from xuanpolicy.tensorflow.representations import Basic_Identical +from xuance.tensorflow.policies import * +from xuance.tensorflow.utils import * +from xuance.tensorflow.representations import Basic_Identical from itertools import chain diff --git a/xuanpolicy/tensorflow/policies/gaussian.py b/xuance/tensorflow/policies/gaussian.py similarity index 98% rename from xuanpolicy/tensorflow/policies/gaussian.py rename to xuance/tensorflow/policies/gaussian.py index 2e6e3be44..3e9449936 100644 --- a/xuanpolicy/tensorflow/policies/gaussian.py +++ b/xuance/tensorflow/policies/gaussian.py @@ -1,6 +1,6 @@ -from xuanpolicy.tensorflow.policies import * -from xuanpolicy.tensorflow.utils import * -from xuanpolicy.tensorflow.representations import Basic_Identical +from xuance.tensorflow.policies import * +from xuance.tensorflow.utils import * +from xuance.tensorflow.representations import Basic_Identical import tensorflow_probability as tfp tfd = tfp.distributions diff --git a/xuanpolicy/tensorflow/policies/gaussian_marl.py b/xuance/tensorflow/policies/gaussian_marl.py similarity index 98% rename from xuanpolicy/tensorflow/policies/gaussian_marl.py rename to xuance/tensorflow/policies/gaussian_marl.py index 9f1c5a54b..72ec17021 100644 --- a/xuanpolicy/tensorflow/policies/gaussian_marl.py +++ b/xuance/tensorflow/policies/gaussian_marl.py @@ -1,6 +1,6 @@ -from xuanpolicy.tensorflow.policies import * -from xuanpolicy.tensorflow.utils import * -from xuanpolicy.tensorflow.representations import Basic_Identical +from xuance.tensorflow.policies import * +from xuance.tensorflow.utils import * +from xuance.tensorflow.representations import Basic_Identical import tensorflow_probability as tfp tfd = tfp.distributions diff --git a/xuanpolicy/tensorflow/policies/mixers.py b/xuance/tensorflow/policies/mixers.py similarity index 100% rename from xuanpolicy/tensorflow/policies/mixers.py rename to xuance/tensorflow/policies/mixers.py diff --git a/xuanpolicy/tensorflow/representations/__init__.py b/xuance/tensorflow/representations/__init__.py similarity index 97% rename from xuanpolicy/tensorflow/representations/__init__.py rename to xuance/tensorflow/representations/__init__.py index aea9cb4c6..8b021086c 100644 --- a/xuanpolicy/tensorflow/representations/__init__.py +++ b/xuance/tensorflow/representations/__init__.py @@ -1,7 +1,7 @@ import tensorflow as tf import numpy as np from typing import Sequence, Union, Optional, Callable -from xuanpolicy.tensorflow.utils.layers import * +from xuance.tensorflow.utils.layers import * from .networks import Basic_Identical, Basic_MLP, Basic_CNN from .networks import CoG_MLP, CoG_RNN, CoG_CNN diff --git a/xuanpolicy/tensorflow/representations/networks.py b/xuance/tensorflow/representations/networks.py similarity index 99% rename from xuanpolicy/tensorflow/representations/networks.py rename to xuance/tensorflow/representations/networks.py index 0316d7fab..69f992971 100644 --- a/xuanpolicy/tensorflow/representations/networks.py +++ b/xuance/tensorflow/representations/networks.py @@ -1,4 +1,4 @@ -from xuanpolicy.tensorflow.representations import * +from xuance.tensorflow.representations import * class Basic_Identical(tk.Model): diff --git a/xuanpolicy/tensorflow/runners/__init__.py b/xuance/tensorflow/runners/__init__.py similarity index 100% rename from xuanpolicy/tensorflow/runners/__init__.py rename to xuance/tensorflow/runners/__init__.py diff --git a/xuanpolicy/tensorflow/runners/runner_basic.py b/xuance/tensorflow/runners/runner_basic.py similarity index 99% rename from xuanpolicy/tensorflow/runners/runner_basic.py rename to xuance/tensorflow/runners/runner_basic.py index 76659af02..2fa3069a9 100644 --- a/xuanpolicy/tensorflow/runners/runner_basic.py +++ b/xuance/tensorflow/runners/runner_basic.py @@ -4,7 +4,7 @@ from pathlib import Path import wandb from torch.utils.tensorboard import SummaryWriter -from xuanpolicy.environment import make_envs +from xuance.environment import make_envs import tensorflow.keras as tk import numpy as np diff --git a/xuanpolicy/tensorflow/runners/runner_drl.py b/xuance/tensorflow/runners/runner_drl.py similarity index 94% rename from xuanpolicy/tensorflow/runners/runner_drl.py rename to xuance/tensorflow/runners/runner_drl.py index 4430feeab..a7a250aa6 100644 --- a/xuanpolicy/tensorflow/runners/runner_drl.py +++ b/xuance/tensorflow/runners/runner_drl.py @@ -1,9 +1,9 @@ from .runner_basic import * -from xuanpolicy.tensorflow.agents import get_total_iters -from xuanpolicy.tensorflow.representations import REGISTRY as REGISTRY_Representation -from xuanpolicy.tensorflow.agents import REGISTRY as REGISTRY_Agent -from xuanpolicy.tensorflow.policies import REGISTRY as REGISTRY_Policy -from xuanpolicy.tensorflow.utils.input_reformat import get_repre_in, get_policy_in +from xuance.tensorflow.agents import get_total_iters +from xuance.tensorflow.representations import REGISTRY as REGISTRY_Representation +from xuance.tensorflow.agents import REGISTRY as REGISTRY_Agent +from xuance.tensorflow.policies import REGISTRY as REGISTRY_Policy +from xuance.tensorflow.utils.input_reformat import get_repre_in, get_policy_in import tensorflow.keras as tk import gym.spaces import numpy as np diff --git a/xuanpolicy/tensorflow/runners/runner_marl.py b/xuance/tensorflow/runners/runner_marl.py similarity index 98% rename from xuanpolicy/tensorflow/runners/runner_marl.py rename to xuance/tensorflow/runners/runner_marl.py index 47627ca71..bfdbe8af3 100644 --- a/xuanpolicy/tensorflow/runners/runner_marl.py +++ b/xuance/tensorflow/runners/runner_marl.py @@ -1,5 +1,5 @@ from .runner_basic import * -from xuanpolicy.tensorflow.agents import REGISTRY as REGISTRY_Agent +from xuance.tensorflow.agents import REGISTRY as REGISTRY_Agent from gym.spaces import Box from tqdm import tqdm import numpy as np diff --git a/xuanpolicy/tensorflow/utils/__init__.py b/xuance/tensorflow/utils/__init__.py similarity index 100% rename from xuanpolicy/tensorflow/utils/__init__.py rename to xuance/tensorflow/utils/__init__.py diff --git a/xuanpolicy/tensorflow/utils/distributions.py b/xuance/tensorflow/utils/distributions.py similarity index 100% rename from xuanpolicy/tensorflow/utils/distributions.py rename to xuance/tensorflow/utils/distributions.py diff --git a/xuanpolicy/tensorflow/utils/input_reformat.py b/xuance/tensorflow/utils/input_reformat.py similarity index 95% rename from xuanpolicy/tensorflow/utils/input_reformat.py rename to xuance/tensorflow/utils/input_reformat.py index 549966fd8..532272d6e 100644 --- a/xuanpolicy/tensorflow/utils/input_reformat.py +++ b/xuance/tensorflow/utils/input_reformat.py @@ -1,7 +1,7 @@ -from xuanpolicy.common import space2shape +from xuance.common import space2shape from copy import deepcopy -from xuanpolicy.tensorflow.policies import Policy_Inputs, Policy_Inputs_All -from xuanpolicy.tensorflow.representations import Representation_Inputs, Representation_Inputs_All +from xuance.tensorflow.policies import Policy_Inputs, Policy_Inputs_All +from xuance.tensorflow.representations import Representation_Inputs, Representation_Inputs_All from operator import itemgetter import tensorflow.keras as tk diff --git a/xuanpolicy/tensorflow/utils/layers.py b/xuance/tensorflow/utils/layers.py similarity index 100% rename from xuanpolicy/tensorflow/utils/layers.py rename to xuance/tensorflow/utils/layers.py diff --git a/xuanpolicy/tensorflow/utils/operations.py b/xuance/tensorflow/utils/operations.py similarity index 100% rename from xuanpolicy/tensorflow/utils/operations.py rename to xuance/tensorflow/utils/operations.py diff --git a/xuanpolicy/torch/__init__.py b/xuance/torch/__init__.py similarity index 100% rename from xuanpolicy/torch/__init__.py rename to xuance/torch/__init__.py diff --git a/xuanpolicy/torch/agents/__init__.py b/xuance/torch/agents/__init__.py similarity index 89% rename from xuanpolicy/torch/agents/__init__.py rename to xuance/torch/agents/__init__.py index 5b5544381..e990145f0 100644 --- a/xuanpolicy/torch/agents/__init__.py +++ b/xuance/torch/agents/__init__.py @@ -8,14 +8,14 @@ import torch import torch.nn as nn import torch.nn.functional as F -from xuanpolicy.environment import * -from xuanpolicy.common import * -from xuanpolicy.torch.learners import * -from xuanpolicy.torch.policies import * -from xuanpolicy.torch.utils import * -from xuanpolicy.torch.policies import REGISTRY as REGISTRY_Policy -from xuanpolicy.torch.utils.input_reformat import get_repre_in, get_policy_in_marl -from xuanpolicy.torch.representations import REGISTRY as REGISTRY_Representation +from xuance.environment import * +from xuance.common import * +from xuance.torch.learners import * +from xuance.torch.policies import * +from xuance.torch.utils import * +from xuance.torch.policies import REGISTRY as REGISTRY_Policy +from xuance.torch.utils.input_reformat import get_repre_in, get_policy_in_marl +from xuance.torch.representations import REGISTRY as REGISTRY_Representation from .agent import Agent, get_total_iters from .agents_marl import MARLAgents, RandomAgents diff --git a/xuanpolicy/torch/agents/agent.py b/xuance/torch/agents/agent.py similarity index 99% rename from xuanpolicy/torch/agents/agent.py rename to xuance/torch/agents/agent.py index e7ae3ba13..3cba0c335 100644 --- a/xuanpolicy/torch/agents/agent.py +++ b/xuance/torch/agents/agent.py @@ -1,7 +1,7 @@ import socket import time from pathlib import Path -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class Agent(ABC): diff --git a/xuanpolicy/torch/agents/agents_marl.py b/xuance/torch/agents/agents_marl.py similarity index 98% rename from xuanpolicy/torch/agents/agents_marl.py rename to xuance/torch/agents/agents_marl.py index 9e3b2b6f8..9492632c8 100644 --- a/xuanpolicy/torch/agents/agents_marl.py +++ b/xuance/torch/agents/agents_marl.py @@ -1,5 +1,5 @@ import os.path -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class MARLAgents(object): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/__init__.py b/xuance/torch/agents/multi_agent_rl/__init__.py similarity index 100% rename from xuanpolicy/torch/agents/multi_agent_rl/__init__.py rename to xuance/torch/agents/multi_agent_rl/__init__.py diff --git a/xuanpolicy/torch/agents/multi_agent_rl/coma_agents.py b/xuance/torch/agents/multi_agent_rl/coma_agents.py similarity index 98% rename from xuanpolicy/torch/agents/multi_agent_rl/coma_agents.py rename to xuance/torch/agents/multi_agent_rl/coma_agents.py index b4d667b45..eb695de5f 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/coma_agents.py +++ b/xuance/torch/agents/multi_agent_rl/coma_agents.py @@ -1,7 +1,7 @@ import torch -from xuanpolicy.torch.agents import * -from xuanpolicy.torch.agents.agents_marl import linear_decay_or_increase +from xuance.torch.agents import * +from xuance.torch.agents.agents_marl import linear_decay_or_increase class COMA_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/dcg_agents.py b/xuance/torch/agents/multi_agent_rl/dcg_agents.py similarity index 96% rename from xuanpolicy/torch/agents/multi_agent_rl/dcg_agents.py rename to xuance/torch/agents/multi_agent_rl/dcg_agents.py index 6f1eeaace..4932d6792 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/dcg_agents.py +++ b/xuance/torch/agents/multi_agent_rl/dcg_agents.py @@ -1,5 +1,5 @@ import torch.nn -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class DCG_Agents(MARLAgents): @@ -22,7 +22,7 @@ def __init__(self, else: representation = REGISTRY_Representation[config.representation](*input_representation) repre_state_dim = representation.output_shapes['state'][0] - from xuanpolicy.torch.policies.coordination_graph import DCG_utility, DCG_payoff, Coordination_Graph + from xuance.torch.policies.coordination_graph import DCG_utility, DCG_payoff, Coordination_Graph utility = DCG_utility(repre_state_dim, config.hidden_utility_dim, config.dim_act).to(device) payoffs = DCG_payoff(repre_state_dim * 2, config.hidden_payoff_dim, config.dim_act, config).to(device) dcgraph = Coordination_Graph(config.n_agents, config.graph_type) @@ -63,7 +63,7 @@ def __init__(self, config.done_shape, envs.num_envs, config.buffer_size, config.batch_size) memory = buffer(*input_buffer, max_episode_length=envs.max_episode_length, dim_act=config.dim_act) - from xuanpolicy.torch.learners.multi_agent_rl.dcg_learner import DCG_Learner + from xuance.torch.learners.multi_agent_rl.dcg_learner import DCG_Learner learner = DCG_Learner(config, policy, optimizer, scheduler, config.device, config.model_dir, config.gamma, config.sync_frequency) diff --git a/xuanpolicy/torch/agents/multi_agent_rl/iddpg_agents.py b/xuance/torch/agents/multi_agent_rl/iddpg_agents.py similarity index 98% rename from xuanpolicy/torch/agents/multi_agent_rl/iddpg_agents.py rename to xuance/torch/agents/multi_agent_rl/iddpg_agents.py index a3667e8e7..4ea12a1f4 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/iddpg_agents.py +++ b/xuance/torch/agents/multi_agent_rl/iddpg_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class IDDPG_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/ippo_agents.py b/xuance/torch/agents/multi_agent_rl/ippo_agents.py similarity index 99% rename from xuanpolicy/torch/agents/multi_agent_rl/ippo_agents.py rename to xuance/torch/agents/multi_agent_rl/ippo_agents.py index d8edfadf2..d225a3fa5 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/ippo_agents.py +++ b/xuance/torch/agents/multi_agent_rl/ippo_agents.py @@ -1,6 +1,6 @@ import torch -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class IPPO_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/iql_agents.py b/xuance/torch/agents/multi_agent_rl/iql_agents.py similarity index 99% rename from xuanpolicy/torch/agents/multi_agent_rl/iql_agents.py rename to xuance/torch/agents/multi_agent_rl/iql_agents.py index 940b89cea..dd23323ae 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/iql_agents.py +++ b/xuance/torch/agents/multi_agent_rl/iql_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class IQL_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/isac_agents.py b/xuance/torch/agents/multi_agent_rl/isac_agents.py similarity index 98% rename from xuanpolicy/torch/agents/multi_agent_rl/isac_agents.py rename to xuance/torch/agents/multi_agent_rl/isac_agents.py index cfd6e26da..e42c6d7d8 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/isac_agents.py +++ b/xuance/torch/agents/multi_agent_rl/isac_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class ISAC_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/maddpg_agents.py b/xuance/torch/agents/multi_agent_rl/maddpg_agents.py similarity index 98% rename from xuanpolicy/torch/agents/multi_agent_rl/maddpg_agents.py rename to xuance/torch/agents/multi_agent_rl/maddpg_agents.py index ba1f30ff0..10ec4180f 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/maddpg_agents.py +++ b/xuance/torch/agents/multi_agent_rl/maddpg_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class MADDPG_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/mappo_agents.py b/xuance/torch/agents/multi_agent_rl/mappo_agents.py similarity index 99% rename from xuanpolicy/torch/agents/multi_agent_rl/mappo_agents.py rename to xuance/torch/agents/multi_agent_rl/mappo_agents.py index c7fa01691..0c7c9e2ba 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/mappo_agents.py +++ b/xuance/torch/agents/multi_agent_rl/mappo_agents.py @@ -1,6 +1,6 @@ import torch -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class MAPPO_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/masac_agents.py b/xuance/torch/agents/multi_agent_rl/masac_agents.py similarity index 98% rename from xuanpolicy/torch/agents/multi_agent_rl/masac_agents.py rename to xuance/torch/agents/multi_agent_rl/masac_agents.py index 639b84ca3..1e68f9854 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/masac_agents.py +++ b/xuance/torch/agents/multi_agent_rl/masac_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class MASAC_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/matd3_agents.py b/xuance/torch/agents/multi_agent_rl/matd3_agents.py similarity index 98% rename from xuanpolicy/torch/agents/multi_agent_rl/matd3_agents.py rename to xuance/torch/agents/multi_agent_rl/matd3_agents.py index c579e8500..9a5ef33de 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/matd3_agents.py +++ b/xuance/torch/agents/multi_agent_rl/matd3_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class MATD3_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/mfac_agents.py b/xuance/torch/agents/multi_agent_rl/mfac_agents.py similarity index 99% rename from xuanpolicy/torch/agents/multi_agent_rl/mfac_agents.py rename to xuance/torch/agents/multi_agent_rl/mfac_agents.py index e7791d23f..ad75ca727 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/mfac_agents.py +++ b/xuance/torch/agents/multi_agent_rl/mfac_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class MFAC_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/mfq_agents.py b/xuance/torch/agents/multi_agent_rl/mfq_agents.py similarity index 97% rename from xuanpolicy/torch/agents/multi_agent_rl/mfq_agents.py rename to xuance/torch/agents/multi_agent_rl/mfq_agents.py index 603757ff3..db4b395d1 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/mfq_agents.py +++ b/xuance/torch/agents/multi_agent_rl/mfq_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.torch.agents import * -from xuanpolicy.torch.agents.agents_marl import linear_decay_or_increase +from xuance.torch.agents import * +from xuance.torch.agents.agents_marl import linear_decay_or_increase class MFQ_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/qmix_agents.py b/xuance/torch/agents/multi_agent_rl/qmix_agents.py similarity index 99% rename from xuanpolicy/torch/agents/multi_agent_rl/qmix_agents.py rename to xuance/torch/agents/multi_agent_rl/qmix_agents.py index f52b83749..a123fd9b7 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/qmix_agents.py +++ b/xuance/torch/agents/multi_agent_rl/qmix_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class QMIX_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/qtran_agents.py b/xuance/torch/agents/multi_agent_rl/qtran_agents.py similarity index 96% rename from xuanpolicy/torch/agents/multi_agent_rl/qtran_agents.py rename to xuance/torch/agents/multi_agent_rl/qtran_agents.py index ffc02f2ea..185e07eb4 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/qtran_agents.py +++ b/xuance/torch/agents/multi_agent_rl/qtran_agents.py @@ -1,5 +1,5 @@ -from xuanpolicy.torch.agents import * -from xuanpolicy.torch.agents.agents_marl import linear_decay_or_increase +from xuance.torch.agents import * +from xuance.torch.agents.agents_marl import linear_decay_or_increase class QTRAN_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/vdac_agents.py b/xuance/torch/agents/multi_agent_rl/vdac_agents.py similarity index 99% rename from xuanpolicy/torch/agents/multi_agent_rl/vdac_agents.py rename to xuance/torch/agents/multi_agent_rl/vdac_agents.py index 3aaf61b09..135130a4b 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/vdac_agents.py +++ b/xuance/torch/agents/multi_agent_rl/vdac_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class VDAC_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/vdn_agents.py b/xuance/torch/agents/multi_agent_rl/vdn_agents.py similarity index 99% rename from xuanpolicy/torch/agents/multi_agent_rl/vdn_agents.py rename to xuance/torch/agents/multi_agent_rl/vdn_agents.py index 82417b2ef..a66661f79 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/vdn_agents.py +++ b/xuance/torch/agents/multi_agent_rl/vdn_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class VDN_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/multi_agent_rl/wqmix_agents.py b/xuance/torch/agents/multi_agent_rl/wqmix_agents.py similarity index 99% rename from xuanpolicy/torch/agents/multi_agent_rl/wqmix_agents.py rename to xuance/torch/agents/multi_agent_rl/wqmix_agents.py index bce8ce7ae..66adb689f 100644 --- a/xuanpolicy/torch/agents/multi_agent_rl/wqmix_agents.py +++ b/xuance/torch/agents/multi_agent_rl/wqmix_agents.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class WQMIX_Agents(MARLAgents): diff --git a/xuanpolicy/torch/agents/policy_gradient/__init__.py b/xuance/torch/agents/policy_gradient/__init__.py similarity index 100% rename from xuanpolicy/torch/agents/policy_gradient/__init__.py rename to xuance/torch/agents/policy_gradient/__init__.py diff --git a/xuanpolicy/torch/agents/policy_gradient/a2c_agent.py b/xuance/torch/agents/policy_gradient/a2c_agent.py similarity index 99% rename from xuanpolicy/torch/agents/policy_gradient/a2c_agent.py rename to xuance/torch/agents/policy_gradient/a2c_agent.py index 3262906c1..24c34bc04 100644 --- a/xuanpolicy/torch/agents/policy_gradient/a2c_agent.py +++ b/xuance/torch/agents/policy_gradient/a2c_agent.py @@ -1,6 +1,6 @@ import numpy as np -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class A2C_Agent(Agent): diff --git a/xuanpolicy/torch/agents/policy_gradient/ddpg_agent.py b/xuance/torch/agents/policy_gradient/ddpg_agent.py similarity index 99% rename from xuanpolicy/torch/agents/policy_gradient/ddpg_agent.py rename to xuance/torch/agents/policy_gradient/ddpg_agent.py index 42399aff0..01160f9c6 100644 --- a/xuanpolicy/torch/agents/policy_gradient/ddpg_agent.py +++ b/xuance/torch/agents/policy_gradient/ddpg_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class DDPG_Agent(Agent): diff --git a/xuanpolicy/torch/agents/policy_gradient/mpdqn_agent.py b/xuance/torch/agents/policy_gradient/mpdqn_agent.py similarity index 99% rename from xuanpolicy/torch/agents/policy_gradient/mpdqn_agent.py rename to xuance/torch/agents/policy_gradient/mpdqn_agent.py index fb177e2cc..140bc8cbc 100644 --- a/xuanpolicy/torch/agents/policy_gradient/mpdqn_agent.py +++ b/xuance/torch/agents/policy_gradient/mpdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * import gym from gym import spaces diff --git a/xuanpolicy/torch/agents/policy_gradient/pdqn_agent.py b/xuance/torch/agents/policy_gradient/pdqn_agent.py similarity index 99% rename from xuanpolicy/torch/agents/policy_gradient/pdqn_agent.py rename to xuance/torch/agents/policy_gradient/pdqn_agent.py index c267fab68..0776acdf3 100644 --- a/xuanpolicy/torch/agents/policy_gradient/pdqn_agent.py +++ b/xuance/torch/agents/policy_gradient/pdqn_agent.py @@ -1,6 +1,6 @@ import numpy as np -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * import gym from gym import spaces diff --git a/xuanpolicy/torch/agents/policy_gradient/pg_agent.py b/xuance/torch/agents/policy_gradient/pg_agent.py similarity index 99% rename from xuanpolicy/torch/agents/policy_gradient/pg_agent.py rename to xuance/torch/agents/policy_gradient/pg_agent.py index ba4d645a3..2dfbb70d1 100644 --- a/xuanpolicy/torch/agents/policy_gradient/pg_agent.py +++ b/xuance/torch/agents/policy_gradient/pg_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class PG_Agent(Agent): diff --git a/xuanpolicy/torch/agents/policy_gradient/ppg_agent.py b/xuance/torch/agents/policy_gradient/ppg_agent.py similarity index 99% rename from xuanpolicy/torch/agents/policy_gradient/ppg_agent.py rename to xuance/torch/agents/policy_gradient/ppg_agent.py index a4f3eb221..993f74843 100644 --- a/xuanpolicy/torch/agents/policy_gradient/ppg_agent.py +++ b/xuance/torch/agents/policy_gradient/ppg_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class PPG_Agent(Agent): diff --git a/xuanpolicy/torch/agents/policy_gradient/ppoclip_agent.py b/xuance/torch/agents/policy_gradient/ppoclip_agent.py similarity index 99% rename from xuanpolicy/torch/agents/policy_gradient/ppoclip_agent.py rename to xuance/torch/agents/policy_gradient/ppoclip_agent.py index cf37ae4e6..ccc37aa13 100644 --- a/xuanpolicy/torch/agents/policy_gradient/ppoclip_agent.py +++ b/xuance/torch/agents/policy_gradient/ppoclip_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class PPOCLIP_Agent(Agent): diff --git a/xuanpolicy/torch/agents/policy_gradient/ppokl_agent.py b/xuance/torch/agents/policy_gradient/ppokl_agent.py similarity index 99% rename from xuanpolicy/torch/agents/policy_gradient/ppokl_agent.py rename to xuance/torch/agents/policy_gradient/ppokl_agent.py index 128acee23..c985ba2ee 100644 --- a/xuanpolicy/torch/agents/policy_gradient/ppokl_agent.py +++ b/xuance/torch/agents/policy_gradient/ppokl_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class PPOKL_Agent(Agent): diff --git a/xuanpolicy/torch/agents/policy_gradient/sac_agent.py b/xuance/torch/agents/policy_gradient/sac_agent.py similarity index 99% rename from xuanpolicy/torch/agents/policy_gradient/sac_agent.py rename to xuance/torch/agents/policy_gradient/sac_agent.py index aa6203d07..5da9a79cf 100644 --- a/xuanpolicy/torch/agents/policy_gradient/sac_agent.py +++ b/xuance/torch/agents/policy_gradient/sac_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class SAC_Agent(Agent): diff --git a/xuanpolicy/torch/agents/policy_gradient/sacdis_agent.py b/xuance/torch/agents/policy_gradient/sacdis_agent.py similarity index 99% rename from xuanpolicy/torch/agents/policy_gradient/sacdis_agent.py rename to xuance/torch/agents/policy_gradient/sacdis_agent.py index 167d65f0b..5009fd79e 100644 --- a/xuanpolicy/torch/agents/policy_gradient/sacdis_agent.py +++ b/xuance/torch/agents/policy_gradient/sacdis_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class SACDIS_Agent(Agent): diff --git a/xuanpolicy/torch/agents/policy_gradient/spdqn_agent.py b/xuance/torch/agents/policy_gradient/spdqn_agent.py similarity index 99% rename from xuanpolicy/torch/agents/policy_gradient/spdqn_agent.py rename to xuance/torch/agents/policy_gradient/spdqn_agent.py index a43ab3428..90fd89698 100644 --- a/xuanpolicy/torch/agents/policy_gradient/spdqn_agent.py +++ b/xuance/torch/agents/policy_gradient/spdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * import gym from gym import spaces diff --git a/xuanpolicy/torch/agents/policy_gradient/td3_agent.py b/xuance/torch/agents/policy_gradient/td3_agent.py similarity index 99% rename from xuanpolicy/torch/agents/policy_gradient/td3_agent.py rename to xuance/torch/agents/policy_gradient/td3_agent.py index 0592d5e45..aa2b4e524 100644 --- a/xuanpolicy/torch/agents/policy_gradient/td3_agent.py +++ b/xuance/torch/agents/policy_gradient/td3_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class TD3_Agent(Agent): diff --git a/xuanpolicy/torch/agents/qlearning_family/__init__.py b/xuance/torch/agents/qlearning_family/__init__.py similarity index 100% rename from xuanpolicy/torch/agents/qlearning_family/__init__.py rename to xuance/torch/agents/qlearning_family/__init__.py diff --git a/xuanpolicy/torch/agents/qlearning_family/c51_agent.py b/xuance/torch/agents/qlearning_family/c51_agent.py similarity index 99% rename from xuanpolicy/torch/agents/qlearning_family/c51_agent.py rename to xuance/torch/agents/qlearning_family/c51_agent.py index c3b0eec1a..f851fd3e6 100644 --- a/xuanpolicy/torch/agents/qlearning_family/c51_agent.py +++ b/xuance/torch/agents/qlearning_family/c51_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class C51_Agent(Agent): diff --git a/xuanpolicy/torch/agents/qlearning_family/ddqn_agent.py b/xuance/torch/agents/qlearning_family/ddqn_agent.py similarity index 99% rename from xuanpolicy/torch/agents/qlearning_family/ddqn_agent.py rename to xuance/torch/agents/qlearning_family/ddqn_agent.py index 43a2d7a7d..8fce93cf9 100644 --- a/xuanpolicy/torch/agents/qlearning_family/ddqn_agent.py +++ b/xuance/torch/agents/qlearning_family/ddqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class DDQN_Agent(Agent): diff --git a/xuanpolicy/torch/agents/qlearning_family/dqn_agent.py b/xuance/torch/agents/qlearning_family/dqn_agent.py similarity index 99% rename from xuanpolicy/torch/agents/qlearning_family/dqn_agent.py rename to xuance/torch/agents/qlearning_family/dqn_agent.py index 593b5d41e..74ae7b70c 100644 --- a/xuanpolicy/torch/agents/qlearning_family/dqn_agent.py +++ b/xuance/torch/agents/qlearning_family/dqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class DQN_Agent(Agent): diff --git a/xuanpolicy/torch/agents/qlearning_family/drqn_agent.py b/xuance/torch/agents/qlearning_family/drqn_agent.py similarity index 99% rename from xuanpolicy/torch/agents/qlearning_family/drqn_agent.py rename to xuance/torch/agents/qlearning_family/drqn_agent.py index c7233237a..e08da0f74 100644 --- a/xuanpolicy/torch/agents/qlearning_family/drqn_agent.py +++ b/xuance/torch/agents/qlearning_family/drqn_agent.py @@ -1,6 +1,6 @@ import numpy as np -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * from collections import deque diff --git a/xuanpolicy/torch/agents/qlearning_family/dueldqn_agent.py b/xuance/torch/agents/qlearning_family/dueldqn_agent.py similarity index 99% rename from xuanpolicy/torch/agents/qlearning_family/dueldqn_agent.py rename to xuance/torch/agents/qlearning_family/dueldqn_agent.py index 9b90a46cc..cde919fea 100644 --- a/xuanpolicy/torch/agents/qlearning_family/dueldqn_agent.py +++ b/xuance/torch/agents/qlearning_family/dueldqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class DuelDQN_Agent(Agent): diff --git a/xuanpolicy/torch/agents/qlearning_family/noisydqn_agent.py b/xuance/torch/agents/qlearning_family/noisydqn_agent.py similarity index 99% rename from xuanpolicy/torch/agents/qlearning_family/noisydqn_agent.py rename to xuance/torch/agents/qlearning_family/noisydqn_agent.py index a31847503..3af545e13 100644 --- a/xuanpolicy/torch/agents/qlearning_family/noisydqn_agent.py +++ b/xuance/torch/agents/qlearning_family/noisydqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class NoisyDQN_Agent(Agent): diff --git a/xuanpolicy/torch/agents/qlearning_family/perdqn_agent.py b/xuance/torch/agents/qlearning_family/perdqn_agent.py similarity index 99% rename from xuanpolicy/torch/agents/qlearning_family/perdqn_agent.py rename to xuance/torch/agents/qlearning_family/perdqn_agent.py index d5356b430..146f6f13a 100644 --- a/xuanpolicy/torch/agents/qlearning_family/perdqn_agent.py +++ b/xuance/torch/agents/qlearning_family/perdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class PerDQN_Agent(Agent): diff --git a/xuanpolicy/torch/agents/qlearning_family/qrdqn_agent.py b/xuance/torch/agents/qlearning_family/qrdqn_agent.py similarity index 99% rename from xuanpolicy/torch/agents/qlearning_family/qrdqn_agent.py rename to xuance/torch/agents/qlearning_family/qrdqn_agent.py index c13cf5fa8..225fda6aa 100644 --- a/xuanpolicy/torch/agents/qlearning_family/qrdqn_agent.py +++ b/xuance/torch/agents/qlearning_family/qrdqn_agent.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.agents import * +from xuance.torch.agents import * class QRDQN_Agent(Agent): diff --git a/xuanpolicy/torch/learners/__init__.py b/xuance/torch/learners/__init__.py similarity index 100% rename from xuanpolicy/torch/learners/__init__.py rename to xuance/torch/learners/__init__.py diff --git a/xuanpolicy/torch/learners/learner.py b/xuance/torch/learners/learner.py similarity index 100% rename from xuanpolicy/torch/learners/learner.py rename to xuance/torch/learners/learner.py diff --git a/xuanpolicy/torch/learners/multi_agent_rl/__init__.py b/xuance/torch/learners/multi_agent_rl/__init__.py similarity index 100% rename from xuanpolicy/torch/learners/multi_agent_rl/__init__.py rename to xuance/torch/learners/multi_agent_rl/__init__.py diff --git a/xuanpolicy/torch/learners/multi_agent_rl/coma_learner.py b/xuance/torch/learners/multi_agent_rl/coma_learner.py similarity index 99% rename from xuanpolicy/torch/learners/multi_agent_rl/coma_learner.py rename to xuance/torch/learners/multi_agent_rl/coma_learner.py index 3c608df46..9a05938fb 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/coma_learner.py +++ b/xuance/torch/learners/multi_agent_rl/coma_learner.py @@ -5,7 +5,7 @@ """ import torch -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class COMA_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/dcg_learner.py b/xuance/torch/learners/multi_agent_rl/dcg_learner.py similarity index 99% rename from xuanpolicy/torch/learners/multi_agent_rl/dcg_learner.py rename to xuance/torch/learners/multi_agent_rl/dcg_learner.py index cb23efeab..f33710c75 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/dcg_learner.py +++ b/xuance/torch/learners/multi_agent_rl/dcg_learner.py @@ -3,7 +3,7 @@ Paper link: http://proceedings.mlr.press/v119/boehmer20a/boehmer20a.pdf Implementation: Pytorch """ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * import torch_scatter diff --git a/xuanpolicy/torch/learners/multi_agent_rl/iddpg_learner.py b/xuance/torch/learners/multi_agent_rl/iddpg_learner.py similarity index 98% rename from xuanpolicy/torch/learners/multi_agent_rl/iddpg_learner.py rename to xuance/torch/learners/multi_agent_rl/iddpg_learner.py index df4dbcbac..4a89ebc47 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/iddpg_learner.py +++ b/xuance/torch/learners/multi_agent_rl/iddpg_learner.py @@ -2,7 +2,7 @@ Independent Deep Deterministic Policy Gradient (IDDPG) Implementation: Pytorch """ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class IDDPG_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/ippo_learner.py b/xuance/torch/learners/multi_agent_rl/ippo_learner.py similarity index 98% rename from xuanpolicy/torch/learners/multi_agent_rl/ippo_learner.py rename to xuance/torch/learners/multi_agent_rl/ippo_learner.py index 437d0bde7..32e121e8a 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/ippo_learner.py +++ b/xuance/torch/learners/multi_agent_rl/ippo_learner.py @@ -4,9 +4,9 @@ https://arxiv.org/pdf/2103.01955.pdf Implementation: Pytorch """ -from xuanpolicy.torch.learners import * -from xuanpolicy.torch.utils.value_norm import ValueNorm -from xuanpolicy.torch.utils.operations import update_linear_decay +from xuance.torch.learners import * +from xuance.torch.utils.value_norm import ValueNorm +from xuance.torch.utils.operations import update_linear_decay class IPPO_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/iql_learner.py b/xuance/torch/learners/multi_agent_rl/iql_learner.py similarity index 99% rename from xuanpolicy/torch/learners/multi_agent_rl/iql_learner.py rename to xuance/torch/learners/multi_agent_rl/iql_learner.py index 371b7c5ec..348baacc9 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/iql_learner.py +++ b/xuance/torch/learners/multi_agent_rl/iql_learner.py @@ -2,7 +2,7 @@ Independent Q-learning (IQL) Implementation: Pytorch """ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class IQL_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/isac_learner.py b/xuance/torch/learners/multi_agent_rl/isac_learner.py similarity index 98% rename from xuanpolicy/torch/learners/multi_agent_rl/isac_learner.py rename to xuance/torch/learners/multi_agent_rl/isac_learner.py index b6b02ff98..3675a48e9 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/isac_learner.py +++ b/xuance/torch/learners/multi_agent_rl/isac_learner.py @@ -2,7 +2,7 @@ Independent Soft Actor-critic (ISAC) Implementation: Pytorch """ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class ISAC_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/maddpg_learner.py b/xuance/torch/learners/multi_agent_rl/maddpg_learner.py similarity index 98% rename from xuanpolicy/torch/learners/multi_agent_rl/maddpg_learner.py rename to xuance/torch/learners/multi_agent_rl/maddpg_learner.py index c4055d001..7b9d619e9 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/maddpg_learner.py +++ b/xuance/torch/learners/multi_agent_rl/maddpg_learner.py @@ -5,7 +5,7 @@ Implementation: Pytorch Trick: Parameter sharing for all agents, with agents' one-hot IDs as actor-critic's inputs. """ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class MADDPG_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/mappo_learner.py b/xuance/torch/learners/multi_agent_rl/mappo_learner.py similarity index 98% rename from xuanpolicy/torch/learners/multi_agent_rl/mappo_learner.py rename to xuance/torch/learners/multi_agent_rl/mappo_learner.py index 7ad5353b2..0108a6a2b 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/mappo_learner.py +++ b/xuance/torch/learners/multi_agent_rl/mappo_learner.py @@ -4,9 +4,9 @@ https://arxiv.org/pdf/2103.01955.pdf Implementation: Pytorch """ -from xuanpolicy.torch.learners import * -from xuanpolicy.torch.utils.value_norm import ValueNorm -from xuanpolicy.torch.utils.operations import update_linear_decay +from xuance.torch.learners import * +from xuance.torch.utils.value_norm import ValueNorm +from xuance.torch.utils.operations import update_linear_decay class MAPPO_Clip_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/masac_learner.py b/xuance/torch/learners/multi_agent_rl/masac_learner.py similarity index 98% rename from xuanpolicy/torch/learners/multi_agent_rl/masac_learner.py rename to xuance/torch/learners/multi_agent_rl/masac_learner.py index 2d0832f86..bd4b34686 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/masac_learner.py +++ b/xuance/torch/learners/multi_agent_rl/masac_learner.py @@ -2,7 +2,7 @@ Multi-agent Soft Actor-critic (MASAC) Implementation: Pytorch """ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class MASAC_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/matd3_learner.py b/xuance/torch/learners/multi_agent_rl/matd3_learner.py similarity index 98% rename from xuanpolicy/torch/learners/multi_agent_rl/matd3_learner.py rename to xuance/torch/learners/multi_agent_rl/matd3_learner.py index a3eb45a39..91b31a663 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/matd3_learner.py +++ b/xuance/torch/learners/multi_agent_rl/matd3_learner.py @@ -1,7 +1,7 @@ """ Multi-Agent TD3 """ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class MATD3_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/mfac_learner.py b/xuance/torch/learners/multi_agent_rl/mfac_learner.py similarity index 99% rename from xuanpolicy/torch/learners/multi_agent_rl/mfac_learner.py rename to xuance/torch/learners/multi_agent_rl/mfac_learner.py index 99c865215..a0d1c6057 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/mfac_learner.py +++ b/xuance/torch/learners/multi_agent_rl/mfac_learner.py @@ -6,7 +6,7 @@ """ import torch -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class MFAC_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/mfq_learner.py b/xuance/torch/learners/multi_agent_rl/mfq_learner.py similarity index 98% rename from xuanpolicy/torch/learners/multi_agent_rl/mfq_learner.py rename to xuance/torch/learners/multi_agent_rl/mfq_learner.py index 29d376a92..e9224a890 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/mfq_learner.py +++ b/xuance/torch/learners/multi_agent_rl/mfq_learner.py @@ -4,7 +4,7 @@ http://proceedings.mlr.press/v80/yang18d/yang18d.pdf Implementation: Pytorch """ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class MFQ_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/qmix_learner.py b/xuance/torch/learners/multi_agent_rl/qmix_learner.py similarity index 99% rename from xuanpolicy/torch/learners/multi_agent_rl/qmix_learner.py rename to xuance/torch/learners/multi_agent_rl/qmix_learner.py index 46cbafd36..bf98685aa 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/qmix_learner.py +++ b/xuance/torch/learners/multi_agent_rl/qmix_learner.py @@ -4,7 +4,7 @@ http://proceedings.mlr.press/v80/rashid18a/rashid18a.pdf Implementation: Pytorch """ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class QMIX_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/qtran_learner.py b/xuance/torch/learners/multi_agent_rl/qtran_learner.py similarity index 99% rename from xuanpolicy/torch/learners/multi_agent_rl/qtran_learner.py rename to xuance/torch/learners/multi_agent_rl/qtran_learner.py index e19f20a06..5fe333135 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/qtran_learner.py +++ b/xuance/torch/learners/multi_agent_rl/qtran_learner.py @@ -4,7 +4,7 @@ http://proceedings.mlr.press/v97/son19a/son19a.pdf Implementation: Pytorch """ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class QTRAN_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/vdac_learner.py b/xuance/torch/learners/multi_agent_rl/vdac_learner.py similarity index 98% rename from xuanpolicy/torch/learners/multi_agent_rl/vdac_learner.py rename to xuance/torch/learners/multi_agent_rl/vdac_learner.py index e9af03c8a..5e0776b5e 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/vdac_learner.py +++ b/xuance/torch/learners/multi_agent_rl/vdac_learner.py @@ -4,9 +4,9 @@ https://ojs.aaai.org/index.php/AAAI/article/view/17353 Implementation: Pytorch """ -from xuanpolicy.torch.learners import * -from xuanpolicy.torch.utils.value_norm import ValueNorm -from xuanpolicy.torch.utils.operations import update_linear_decay +from xuance.torch.learners import * +from xuance.torch.utils.value_norm import ValueNorm +from xuance.torch.utils.operations import update_linear_decay class VDAC_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/vdn_learner.py b/xuance/torch/learners/multi_agent_rl/vdn_learner.py similarity index 99% rename from xuanpolicy/torch/learners/multi_agent_rl/vdn_learner.py rename to xuance/torch/learners/multi_agent_rl/vdn_learner.py index 17c763a72..774991498 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/vdn_learner.py +++ b/xuance/torch/learners/multi_agent_rl/vdn_learner.py @@ -4,7 +4,7 @@ https://arxiv.org/pdf/1706.05296.pdf Implementation: Pytorch """ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class VDN_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/multi_agent_rl/wqmix_learner.py b/xuance/torch/learners/multi_agent_rl/wqmix_learner.py similarity index 99% rename from xuanpolicy/torch/learners/multi_agent_rl/wqmix_learner.py rename to xuance/torch/learners/multi_agent_rl/wqmix_learner.py index 160aa662e..7b13bb8ab 100644 --- a/xuanpolicy/torch/learners/multi_agent_rl/wqmix_learner.py +++ b/xuance/torch/learners/multi_agent_rl/wqmix_learner.py @@ -4,7 +4,7 @@ https://proceedings.neurips.cc/paper/2020/file/73a427badebe0e32caa2e1fc7530b7f3-Paper.pdf Implementation: Pytorch """ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class WQMIX_Learner(LearnerMAS): diff --git a/xuanpolicy/torch/learners/policy_gradient/__init__.py b/xuance/torch/learners/policy_gradient/__init__.py similarity index 100% rename from xuanpolicy/torch/learners/policy_gradient/__init__.py rename to xuance/torch/learners/policy_gradient/__init__.py diff --git a/xuanpolicy/torch/learners/policy_gradient/a2c_learner.py b/xuance/torch/learners/policy_gradient/a2c_learner.py similarity index 97% rename from xuanpolicy/torch/learners/policy_gradient/a2c_learner.py rename to xuance/torch/learners/policy_gradient/a2c_learner.py index 38a86a8b5..e6340fb8f 100644 --- a/xuanpolicy/torch/learners/policy_gradient/a2c_learner.py +++ b/xuance/torch/learners/policy_gradient/a2c_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class A2C_Learner(Learner): diff --git a/xuanpolicy/torch/learners/policy_gradient/ddpg_learner.py b/xuance/torch/learners/policy_gradient/ddpg_learner.py similarity index 98% rename from xuanpolicy/torch/learners/policy_gradient/ddpg_learner.py rename to xuance/torch/learners/policy_gradient/ddpg_learner.py index c7c4644e5..a2851154d 100644 --- a/xuanpolicy/torch/learners/policy_gradient/ddpg_learner.py +++ b/xuance/torch/learners/policy_gradient/ddpg_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class DDPG_Learner(Learner): diff --git a/xuanpolicy/torch/learners/policy_gradient/mpdqn_learner.py b/xuance/torch/learners/policy_gradient/mpdqn_learner.py similarity index 98% rename from xuanpolicy/torch/learners/policy_gradient/mpdqn_learner.py rename to xuance/torch/learners/policy_gradient/mpdqn_learner.py index 27bc3bc0e..c4733d654 100644 --- a/xuanpolicy/torch/learners/policy_gradient/mpdqn_learner.py +++ b/xuance/torch/learners/policy_gradient/mpdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class MPDQN_Learner(Learner): diff --git a/xuanpolicy/torch/learners/policy_gradient/pdqn_learner.py b/xuance/torch/learners/policy_gradient/pdqn_learner.py similarity index 98% rename from xuanpolicy/torch/learners/policy_gradient/pdqn_learner.py rename to xuance/torch/learners/policy_gradient/pdqn_learner.py index d90c78612..cad1f966f 100644 --- a/xuanpolicy/torch/learners/policy_gradient/pdqn_learner.py +++ b/xuance/torch/learners/policy_gradient/pdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class PDQN_Learner(Learner): def __init__(self, diff --git a/xuanpolicy/torch/learners/policy_gradient/pg_learner.py b/xuance/torch/learners/policy_gradient/pg_learner.py similarity index 97% rename from xuanpolicy/torch/learners/policy_gradient/pg_learner.py rename to xuance/torch/learners/policy_gradient/pg_learner.py index f7ca8c9d6..a3ba26578 100644 --- a/xuanpolicy/torch/learners/policy_gradient/pg_learner.py +++ b/xuance/torch/learners/policy_gradient/pg_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class PG_Learner(Learner): diff --git a/xuanpolicy/torch/learners/policy_gradient/ppg_learner.py b/xuance/torch/learners/policy_gradient/ppg_learner.py similarity index 97% rename from xuanpolicy/torch/learners/policy_gradient/ppg_learner.py rename to xuance/torch/learners/policy_gradient/ppg_learner.py index 3de2484d3..c482be176 100644 --- a/xuanpolicy/torch/learners/policy_gradient/ppg_learner.py +++ b/xuance/torch/learners/policy_gradient/ppg_learner.py @@ -1,5 +1,5 @@ -from xuanpolicy.torch.learners import * -from xuanpolicy.torch.utils.operations import merge_distributions +from xuance.torch.learners import * +from xuance.torch.utils.operations import merge_distributions class PPG_Learner(Learner): diff --git a/xuanpolicy/torch/learners/policy_gradient/ppoclip_learner.py b/xuance/torch/learners/policy_gradient/ppoclip_learner.py similarity index 98% rename from xuanpolicy/torch/learners/policy_gradient/ppoclip_learner.py rename to xuance/torch/learners/policy_gradient/ppoclip_learner.py index 5d5b183e1..6019f849c 100644 --- a/xuanpolicy/torch/learners/policy_gradient/ppoclip_learner.py +++ b/xuance/torch/learners/policy_gradient/ppoclip_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class PPOCLIP_Learner(Learner): diff --git a/xuanpolicy/torch/learners/policy_gradient/ppokl_learner.py b/xuance/torch/learners/policy_gradient/ppokl_learner.py similarity index 95% rename from xuanpolicy/torch/learners/policy_gradient/ppokl_learner.py rename to xuance/torch/learners/policy_gradient/ppokl_learner.py index dd00b561b..e2be8cb27 100644 --- a/xuanpolicy/torch/learners/policy_gradient/ppokl_learner.py +++ b/xuance/torch/learners/policy_gradient/ppokl_learner.py @@ -1,5 +1,5 @@ -from xuanpolicy.torch.learners import * -from xuanpolicy.torch.utils.operations import merge_distributions +from xuance.torch.learners import * +from xuance.torch.utils.operations import merge_distributions class PPOKL_Learner(Learner): diff --git a/xuanpolicy/torch/learners/policy_gradient/sac_learner.py b/xuance/torch/learners/policy_gradient/sac_learner.py similarity index 98% rename from xuanpolicy/torch/learners/policy_gradient/sac_learner.py rename to xuance/torch/learners/policy_gradient/sac_learner.py index cfa162c68..f6f94bd6d 100644 --- a/xuanpolicy/torch/learners/policy_gradient/sac_learner.py +++ b/xuance/torch/learners/policy_gradient/sac_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class SAC_Learner(Learner): diff --git a/xuanpolicy/torch/learners/policy_gradient/sacdis_learner.py b/xuance/torch/learners/policy_gradient/sacdis_learner.py similarity index 98% rename from xuanpolicy/torch/learners/policy_gradient/sacdis_learner.py rename to xuance/torch/learners/policy_gradient/sacdis_learner.py index 41822c538..e326e351a 100644 --- a/xuanpolicy/torch/learners/policy_gradient/sacdis_learner.py +++ b/xuance/torch/learners/policy_gradient/sacdis_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class SACDIS_Learner(Learner): diff --git a/xuanpolicy/torch/learners/policy_gradient/spdqn_learner.py b/xuance/torch/learners/policy_gradient/spdqn_learner.py similarity index 98% rename from xuanpolicy/torch/learners/policy_gradient/spdqn_learner.py rename to xuance/torch/learners/policy_gradient/spdqn_learner.py index a3787d300..0ce85d337 100644 --- a/xuanpolicy/torch/learners/policy_gradient/spdqn_learner.py +++ b/xuance/torch/learners/policy_gradient/spdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class SPDQN_Learner(Learner): diff --git a/xuanpolicy/torch/learners/policy_gradient/td3_learner.py b/xuance/torch/learners/policy_gradient/td3_learner.py similarity index 98% rename from xuanpolicy/torch/learners/policy_gradient/td3_learner.py rename to xuance/torch/learners/policy_gradient/td3_learner.py index b93c294df..d4d148f95 100644 --- a/xuanpolicy/torch/learners/policy_gradient/td3_learner.py +++ b/xuance/torch/learners/policy_gradient/td3_learner.py @@ -2,7 +2,7 @@ # 1. noisy action in target actor # 2. double critic network # 3. delayed actor update -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class TD3_Learner(Learner): diff --git a/xuanpolicy/torch/learners/qlearning_family/__init__.py b/xuance/torch/learners/qlearning_family/__init__.py similarity index 100% rename from xuanpolicy/torch/learners/qlearning_family/__init__.py rename to xuance/torch/learners/qlearning_family/__init__.py diff --git a/xuanpolicy/torch/learners/qlearning_family/c51_learner.py b/xuance/torch/learners/qlearning_family/c51_learner.py similarity index 98% rename from xuanpolicy/torch/learners/qlearning_family/c51_learner.py rename to xuance/torch/learners/qlearning_family/c51_learner.py index e785515b5..c8858b0ee 100644 --- a/xuanpolicy/torch/learners/qlearning_family/c51_learner.py +++ b/xuance/torch/learners/qlearning_family/c51_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class C51_Learner(Learner): diff --git a/xuanpolicy/torch/learners/qlearning_family/ddqn_learner.py b/xuance/torch/learners/qlearning_family/ddqn_learner.py similarity index 97% rename from xuanpolicy/torch/learners/qlearning_family/ddqn_learner.py rename to xuance/torch/learners/qlearning_family/ddqn_learner.py index 4d73372ac..00ec47b42 100644 --- a/xuanpolicy/torch/learners/qlearning_family/ddqn_learner.py +++ b/xuance/torch/learners/qlearning_family/ddqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class DDQN_Learner(Learner): diff --git a/xuanpolicy/torch/learners/qlearning_family/dqn_learner.py b/xuance/torch/learners/qlearning_family/dqn_learner.py similarity index 97% rename from xuanpolicy/torch/learners/qlearning_family/dqn_learner.py rename to xuance/torch/learners/qlearning_family/dqn_learner.py index 3f1971380..d19046507 100644 --- a/xuanpolicy/torch/learners/qlearning_family/dqn_learner.py +++ b/xuance/torch/learners/qlearning_family/dqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class DQN_Learner(Learner): diff --git a/xuanpolicy/torch/learners/qlearning_family/drqn_learner.py b/xuance/torch/learners/qlearning_family/drqn_learner.py similarity index 98% rename from xuanpolicy/torch/learners/qlearning_family/drqn_learner.py rename to xuance/torch/learners/qlearning_family/drqn_learner.py index 8cb12d507..af2d705e6 100644 --- a/xuanpolicy/torch/learners/qlearning_family/drqn_learner.py +++ b/xuance/torch/learners/qlearning_family/drqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class DRQN_Learner(Learner): diff --git a/xuanpolicy/torch/learners/qlearning_family/dueldqn_learner.py b/xuance/torch/learners/qlearning_family/dueldqn_learner.py similarity index 97% rename from xuanpolicy/torch/learners/qlearning_family/dueldqn_learner.py rename to xuance/torch/learners/qlearning_family/dueldqn_learner.py index 7513e3f57..8af3755d4 100644 --- a/xuanpolicy/torch/learners/qlearning_family/dueldqn_learner.py +++ b/xuance/torch/learners/qlearning_family/dueldqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class DuelDQN_Learner(Learner): diff --git a/xuanpolicy/torch/learners/qlearning_family/perdqn_learner.py b/xuance/torch/learners/qlearning_family/perdqn_learner.py similarity index 97% rename from xuanpolicy/torch/learners/qlearning_family/perdqn_learner.py rename to xuance/torch/learners/qlearning_family/perdqn_learner.py index 49dfd4031..6485192a8 100644 --- a/xuanpolicy/torch/learners/qlearning_family/perdqn_learner.py +++ b/xuance/torch/learners/qlearning_family/perdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class PerDQN_Learner(Learner): diff --git a/xuanpolicy/torch/learners/qlearning_family/qrdqn_learner.py b/xuance/torch/learners/qlearning_family/qrdqn_learner.py similarity index 97% rename from xuanpolicy/torch/learners/qlearning_family/qrdqn_learner.py rename to xuance/torch/learners/qlearning_family/qrdqn_learner.py index 4e0973721..7d18e94c3 100644 --- a/xuanpolicy/torch/learners/qlearning_family/qrdqn_learner.py +++ b/xuance/torch/learners/qlearning_family/qrdqn_learner.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.learners import * +from xuance.torch.learners import * class QRDQN_Learner(Learner): diff --git a/xuanpolicy/torch/learners/ssl_rl/__init__.py b/xuance/torch/learners/ssl_rl/__init__.py similarity index 100% rename from xuanpolicy/torch/learners/ssl_rl/__init__.py rename to xuance/torch/learners/ssl_rl/__init__.py diff --git a/xuanpolicy/torch/learners/ssl_rl/curl_learner.py b/xuance/torch/learners/ssl_rl/curl_learner.py similarity index 100% rename from xuanpolicy/torch/learners/ssl_rl/curl_learner.py rename to xuance/torch/learners/ssl_rl/curl_learner.py diff --git a/xuanpolicy/torch/policies/__init__.py b/xuance/torch/policies/__init__.py similarity index 100% rename from xuanpolicy/torch/policies/__init__.py rename to xuance/torch/policies/__init__.py diff --git a/xuanpolicy/torch/policies/categorical.py b/xuance/torch/policies/categorical.py similarity index 98% rename from xuanpolicy/torch/policies/categorical.py rename to xuance/torch/policies/categorical.py index a9b7ab58f..a5adf54e5 100644 --- a/xuanpolicy/torch/policies/categorical.py +++ b/xuance/torch/policies/categorical.py @@ -2,9 +2,9 @@ import torch.distributions -from xuanpolicy.torch.policies import * -from xuanpolicy.torch.utils import * -from xuanpolicy.torch.representations import Basic_Identical +from xuance.torch.policies import * +from xuance.torch.utils import * +from xuance.torch.representations import Basic_Identical def _init_layer(layer, gain=np.sqrt(2), bias=0.0): diff --git a/xuanpolicy/torch/policies/categorical_marl.py b/xuance/torch/policies/categorical_marl.py similarity index 98% rename from xuanpolicy/torch/policies/categorical_marl.py rename to xuance/torch/policies/categorical_marl.py index 2f9b2583b..23e1e98ac 100644 --- a/xuanpolicy/torch/policies/categorical_marl.py +++ b/xuance/torch/policies/categorical_marl.py @@ -1,8 +1,8 @@ import torch -from xuanpolicy.torch.policies import * -from xuanpolicy.torch.utils import * -from xuanpolicy.torch.representations import Basic_Identical +from xuance.torch.policies import * +from xuance.torch.utils import * +from xuance.torch.representations import Basic_Identical from .deterministic_marl import BasicQhead diff --git a/xuanpolicy/torch/policies/coordination_graph.py b/xuance/torch/policies/coordination_graph.py similarity index 100% rename from xuanpolicy/torch/policies/coordination_graph.py rename to xuance/torch/policies/coordination_graph.py diff --git a/xuanpolicy/torch/policies/deterministic.py b/xuance/torch/policies/deterministic.py similarity index 99% rename from xuanpolicy/torch/policies/deterministic.py rename to xuance/torch/policies/deterministic.py index 433bb99e8..5dcc58696 100644 --- a/xuanpolicy/torch/policies/deterministic.py +++ b/xuance/torch/policies/deterministic.py @@ -1,6 +1,6 @@ -from xuanpolicy.torch.policies import * -from xuanpolicy.torch.utils import * -from xuanpolicy.torch.representations import Basic_Identical +from xuance.torch.policies import * +from xuance.torch.utils import * +from xuance.torch.representations import Basic_Identical class BasicQhead(nn.Module): diff --git a/xuanpolicy/torch/policies/deterministic_marl.py b/xuance/torch/policies/deterministic_marl.py similarity index 99% rename from xuanpolicy/torch/policies/deterministic_marl.py rename to xuance/torch/policies/deterministic_marl.py index 58afb397d..17410987b 100644 --- a/xuanpolicy/torch/policies/deterministic_marl.py +++ b/xuance/torch/policies/deterministic_marl.py @@ -3,9 +3,9 @@ import numpy as np import torch -from xuanpolicy.torch.policies import * -from xuanpolicy.torch.utils import * -from xuanpolicy.torch.representations import Basic_Identical +from xuance.torch.policies import * +from xuance.torch.utils import * +from xuance.torch.representations import Basic_Identical from gymnasium.spaces.box import Box as Box_pettingzoo from gymnasium import spaces as spaces_pettingzoo diff --git a/xuanpolicy/torch/policies/gaussian.py b/xuance/torch/policies/gaussian.py similarity index 98% rename from xuanpolicy/torch/policies/gaussian.py rename to xuance/torch/policies/gaussian.py index d23e42497..535f767ad 100644 --- a/xuanpolicy/torch/policies/gaussian.py +++ b/xuance/torch/policies/gaussian.py @@ -1,8 +1,8 @@ import copy -from xuanpolicy.torch.policies import * -from xuanpolicy.torch.utils import * -from xuanpolicy.torch.representations import Basic_Identical +from xuance.torch.policies import * +from xuance.torch.utils import * +from xuance.torch.representations import Basic_Identical class ActorNet(nn.Module): diff --git a/xuanpolicy/torch/policies/gaussian_marl.py b/xuance/torch/policies/gaussian_marl.py similarity index 98% rename from xuanpolicy/torch/policies/gaussian_marl.py rename to xuance/torch/policies/gaussian_marl.py index 3a73a81e9..6ed1f5c22 100644 --- a/xuanpolicy/torch/policies/gaussian_marl.py +++ b/xuance/torch/policies/gaussian_marl.py @@ -1,8 +1,8 @@ import torch.distributions -from xuanpolicy.torch.policies import * -from xuanpolicy.torch.utils import * -from xuanpolicy.torch.representations import Basic_Identical +from xuance.torch.policies import * +from xuance.torch.utils import * +from xuance.torch.representations import Basic_Identical from gymnasium.spaces.box import Box as Box_pettingzoo diff --git a/xuanpolicy/torch/policies/mixers.py b/xuance/torch/policies/mixers.py similarity index 100% rename from xuanpolicy/torch/policies/mixers.py rename to xuance/torch/policies/mixers.py diff --git a/xuanpolicy/torch/representations/__init__.py b/xuance/torch/representations/__init__.py similarity index 97% rename from xuanpolicy/torch/representations/__init__.py rename to xuance/torch/representations/__init__.py index 4ac5d1da9..5264ecdff 100644 --- a/xuanpolicy/torch/representations/__init__.py +++ b/xuance/torch/representations/__init__.py @@ -3,7 +3,7 @@ import torch.nn.functional as F import numpy as np from typing import Sequence, Union, Optional, Callable -from xuanpolicy.torch.utils.layers import * +from xuance.torch.utils.layers import * from .mlp import Basic_Identical, Basic_MLP from .cnn import Basic_CNN, AC_CNN_Atari diff --git a/xuanpolicy/torch/representations/cnn.py b/xuance/torch/representations/cnn.py similarity index 98% rename from xuanpolicy/torch/representations/cnn.py rename to xuance/torch/representations/cnn.py index fe81814e9..422a2f405 100644 --- a/xuanpolicy/torch/representations/cnn.py +++ b/xuance/torch/representations/cnn.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.representations import * +from xuance.torch.representations import * # process the input observations with stacks of CNN layers diff --git a/xuanpolicy/torch/representations/mlp.py b/xuance/torch/representations/mlp.py similarity index 97% rename from xuanpolicy/torch/representations/mlp.py rename to xuance/torch/representations/mlp.py index 63393b11d..81886c4d8 100644 --- a/xuanpolicy/torch/representations/mlp.py +++ b/xuance/torch/representations/mlp.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.representations import * +from xuance.torch.representations import * # directly returns the original observation diff --git a/xuanpolicy/torch/representations/rnn.py b/xuance/torch/representations/rnn.py similarity index 98% rename from xuanpolicy/torch/representations/rnn.py rename to xuance/torch/representations/rnn.py index 56d6c5f07..d113654ac 100644 --- a/xuanpolicy/torch/representations/rnn.py +++ b/xuance/torch/representations/rnn.py @@ -1,4 +1,4 @@ -from xuanpolicy.torch.representations import * +from xuance.torch.representations import * class Basic_RNN(nn.Module): diff --git a/xuanpolicy/torch/runners/__init__.py b/xuance/torch/runners/__init__.py similarity index 100% rename from xuanpolicy/torch/runners/__init__.py rename to xuance/torch/runners/__init__.py diff --git a/xuanpolicy/torch/runners/runner_basic.py b/xuance/torch/runners/runner_basic.py similarity index 73% rename from xuanpolicy/torch/runners/runner_basic.py rename to xuance/torch/runners/runner_basic.py index 3cfa0c2b8..23ef921a1 100644 --- a/xuanpolicy/torch/runners/runner_basic.py +++ b/xuance/torch/runners/runner_basic.py @@ -1,5 +1,5 @@ -from xuanpolicy.environment import make_envs -from xuanpolicy.torch.utils.operations import set_seed +from xuance.environment import make_envs +from xuance.torch.utils.operations import set_seed class Runner_Base(object): diff --git a/xuanpolicy/torch/runners/runner_drl.py b/xuance/torch/runners/runner_drl.py similarity index 94% rename from xuanpolicy/torch/runners/runner_drl.py rename to xuance/torch/runners/runner_drl.py index c2335372d..53de7ef21 100644 --- a/xuanpolicy/torch/runners/runner_drl.py +++ b/xuance/torch/runners/runner_drl.py @@ -1,11 +1,11 @@ import wandb from .runner_basic import * -from xuanpolicy.torch.agents import get_total_iters -from xuanpolicy.torch.representations import REGISTRY as REGISTRY_Representation -from xuanpolicy.torch.agents import REGISTRY as REGISTRY_Agent -from xuanpolicy.torch.policies import REGISTRY as REGISTRY_Policy -from xuanpolicy.torch.utils.input_reformat import get_repre_in, get_policy_in -from xuanpolicy.torch.utils.operations import set_seed +from xuance.torch.agents import get_total_iters +from xuance.torch.representations import REGISTRY as REGISTRY_Representation +from xuance.torch.agents import REGISTRY as REGISTRY_Agent +from xuance.torch.policies import REGISTRY as REGISTRY_Policy +from xuance.torch.utils.input_reformat import get_repre_in, get_policy_in +from xuance.torch.utils.operations import set_seed import itertools import torch import gym.spaces diff --git a/xuanpolicy/torch/runners/runner_football.py b/xuance/torch/runners/runner_football.py similarity index 100% rename from xuanpolicy/torch/runners/runner_football.py rename to xuance/torch/runners/runner_football.py diff --git a/xuanpolicy/torch/runners/runner_magent.py b/xuance/torch/runners/runner_magent.py similarity index 100% rename from xuanpolicy/torch/runners/runner_magent.py rename to xuance/torch/runners/runner_magent.py diff --git a/xuanpolicy/torch/runners/runner_pettingzoo.py b/xuance/torch/runners/runner_pettingzoo.py similarity index 99% rename from xuanpolicy/torch/runners/runner_pettingzoo.py rename to xuance/torch/runners/runner_pettingzoo.py index 49b711a7b..d18bd8930 100644 --- a/xuanpolicy/torch/runners/runner_pettingzoo.py +++ b/xuance/torch/runners/runner_pettingzoo.py @@ -5,7 +5,7 @@ import wandb from torch.utils.tensorboard import SummaryWriter from .runner_basic import Runner_Base, make_envs -from xuanpolicy.torch.agents import REGISTRY as REGISTRY_Agent +from xuance.torch.agents import REGISTRY as REGISTRY_Agent from gymnasium.spaces.box import Box from tqdm import tqdm import numpy as np diff --git a/xuanpolicy/torch/runners/runner_sc2.py b/xuance/torch/runners/runner_sc2.py similarity index 99% rename from xuanpolicy/torch/runners/runner_sc2.py rename to xuance/torch/runners/runner_sc2.py index cb2e02134..f13e28264 100644 --- a/xuanpolicy/torch/runners/runner_sc2.py +++ b/xuance/torch/runners/runner_sc2.py @@ -2,7 +2,7 @@ import socket from pathlib import Path from .runner_basic import Runner_Base, make_envs -from xuanpolicy.torch.agents import REGISTRY as REGISTRY_Agent +from xuance.torch.agents import REGISTRY as REGISTRY_Agent import wandb from torch.utils.tensorboard import SummaryWriter import time diff --git a/xuanpolicy/torch/utils/__init__.py b/xuance/torch/utils/__init__.py similarity index 100% rename from xuanpolicy/torch/utils/__init__.py rename to xuance/torch/utils/__init__.py diff --git a/xuanpolicy/torch/utils/distributions.py b/xuance/torch/utils/distributions.py similarity index 100% rename from xuanpolicy/torch/utils/distributions.py rename to xuance/torch/utils/distributions.py diff --git a/xuanpolicy/torch/utils/input_reformat.py b/xuance/torch/utils/input_reformat.py similarity index 94% rename from xuanpolicy/torch/utils/input_reformat.py rename to xuance/torch/utils/input_reformat.py index 7229a6fe5..7c2784446 100644 --- a/xuanpolicy/torch/utils/input_reformat.py +++ b/xuance/torch/utils/input_reformat.py @@ -1,8 +1,8 @@ -from xuanpolicy.common import space2shape +from xuance.common import space2shape from copy import deepcopy -from xuanpolicy.torch.utils import ActivationFunctions, NormalizeFunctions, InitializeFunctions -from xuanpolicy.torch.policies import Policy_Inputs, Policy_Inputs_All -from xuanpolicy.torch.representations import Representation_Inputs, Representation_Inputs_All +from xuance.torch.utils import ActivationFunctions, NormalizeFunctions, InitializeFunctions +from xuance.torch.policies import Policy_Inputs, Policy_Inputs_All +from xuance.torch.representations import Representation_Inputs, Representation_Inputs_All from operator import itemgetter import torch diff --git a/xuanpolicy/torch/utils/layers.py b/xuance/torch/utils/layers.py similarity index 100% rename from xuanpolicy/torch/utils/layers.py rename to xuance/torch/utils/layers.py diff --git a/xuanpolicy/torch/utils/operations.py b/xuance/torch/utils/operations.py similarity index 100% rename from xuanpolicy/torch/utils/operations.py rename to xuance/torch/utils/operations.py diff --git a/xuanpolicy/torch/utils/value_norm.py b/xuance/torch/utils/value_norm.py similarity index 100% rename from xuanpolicy/torch/utils/value_norm.py rename to xuance/torch/utils/value_norm.py diff --git a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/details.md b/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/details.md deleted file mode 100644 index c0d994165..000000000 --- a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/details.md +++ /dev/null @@ -1,581 +0,0 @@ -# Details - -Date : 2023-08-23 15:10:05 - -Directory /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy - -Total : 566 files, 43396 codes, 2416 comments, 6986 blanks, all 52798 lines - -[Summary](results.md) / Details / [Diff Summary](diff.md) / [Diff Details](diff-details.md) - -## Files -| filename | language | code | comment | blank | total | -| :--- | :--- | ---: | ---: | ---: | ---: | -| [__init__.py](/__init__.py) | Python | 4 | 0 | 1 | 5 | -| [common/__init__.py](/common/__init__.py) | Python | 5 | 0 | 1 | 6 | -| [common/common_tools.py](/common/common_tools.py) | Python | 151 | 18 | 29 | 198 | -| [common/memory_tools.py](/common/memory_tools.py) | Python | 397 | 91 | 70 | 558 | -| [common/memory_tools_marl.py](/common/memory_tools_marl.py) | Python | 377 | 106 | 61 | 544 | -| [common/segtree_tool.py](/common/segtree_tool.py) | Python | 69 | 3 | 15 | 87 | -| [common/statistic_tools.py](/common/statistic_tools.py) | Python | 115 | 0 | 13 | 128 | -| [configs/__init__.py](/configs/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [configs/a2c/atari.yaml](/configs/a2c/atari.yaml) | YAML | 41 | 1 | 6 | 48 | -| [configs/a2c/box2d/BipedalWalker-v3.yaml](/configs/a2c/box2d/BipedalWalker-v3.yaml) | YAML | 32 | 0 | 6 | 38 | -| [configs/a2c/box2d/LunarLander-v2.yaml](/configs/a2c/box2d/LunarLander-v2.yaml) | YAML | 32 | 0 | 6 | 38 | -| [configs/a2c/classic_control/Acrobot-v1.yaml](/configs/a2c/classic_control/Acrobot-v1.yaml) | YAML | 33 | 0 | 6 | 39 | -| [configs/a2c/classic_control/CartPole-v1.yaml](/configs/a2c/classic_control/CartPole-v1.yaml) | YAML | 33 | 0 | 6 | 39 | -| [configs/a2c/classic_control/MountainCar-v0.yaml](/configs/a2c/classic_control/MountainCar-v0.yaml) | YAML | 33 | 0 | 6 | 39 | -| [configs/a2c/classic_control/Pendulum-v1.yaml](/configs/a2c/classic_control/Pendulum-v1.yaml) | YAML | 33 | 0 | 6 | 39 | -| [configs/a2c/mujoco.yaml](/configs/a2c/mujoco.yaml) | YAML | 33 | 0 | 6 | 39 | -| [configs/basic.yaml](/configs/basic.yaml) | YAML | 13 | 3 | 6 | 22 | -| [configs/c51/atari.yaml](/configs/c51/atari.yaml) | YAML | 41 | 1 | 7 | 49 | -| [configs/c51/box2d/CarRacing-v2.yaml](/configs/c51/box2d/CarRacing-v2.yaml) | YAML | 35 | 1 | 7 | 43 | -| [configs/c51/box2d/LunarLander-v2.yaml](/configs/c51/box2d/LunarLander-v2.yaml) | YAML | 33 | 0 | 6 | 39 | -| [configs/c51/classic_control/Acrobot-v1.yaml](/configs/c51/classic_control/Acrobot-v1.yaml) | YAML | 33 | 0 | 6 | 39 | -| [configs/c51/classic_control/CartPole-v1.yaml](/configs/c51/classic_control/CartPole-v1.yaml) | YAML | 33 | 0 | 6 | 39 | -| [configs/c51/classic_control/MountainCar-v0.yaml](/configs/c51/classic_control/MountainCar-v0.yaml) | YAML | 33 | 0 | 6 | 39 | -| [configs/coma/mpe/simple_spread_v3.yaml](/configs/coma/mpe/simple_spread_v3.yaml) | YAML | 38 | 0 | 7 | 45 | -| [configs/dcg/mpe/simple_spread_v3.yaml](/configs/dcg/mpe/simple_spread_v3.yaml) | YAML | 44 | 0 | 8 | 52 | -| [configs/dcg/sc2/25m.yaml](/configs/dcg/sc2/25m.yaml) | YAML | 49 | 1 | 8 | 58 | -| [configs/dcg/sc2/2m_vs_1z.yaml](/configs/dcg/sc2/2m_vs_1z.yaml) | YAML | 49 | 1 | 8 | 58 | -| [configs/dcg/sc2/3m.yaml](/configs/dcg/sc2/3m.yaml) | YAML | 49 | 1 | 8 | 58 | -| [configs/dcg/sc2/5m_vs_6m.yaml](/configs/dcg/sc2/5m_vs_6m.yaml) | YAML | 49 | 1 | 8 | 58 | -| [configs/dcg/sc2/8m.yaml](/configs/dcg/sc2/8m.yaml) | YAML | 49 | 1 | 8 | 58 | -| [configs/dcg/sc2/8m_vs_9m.yaml](/configs/dcg/sc2/8m_vs_9m.yaml) | YAML | 49 | 1 | 8 | 58 | -| [configs/dcg/sc2/MMM2.yaml](/configs/dcg/sc2/MMM2.yaml) | YAML | 49 | 1 | 8 | 58 | -| [configs/dcg/sc2/corridor.yaml](/configs/dcg/sc2/corridor.yaml) | YAML | 49 | 1 | 8 | 58 | -| [configs/ddpg/box2d/BipedalWalker-v3.yaml](/configs/ddpg/box2d/BipedalWalker-v3.yaml) | YAML | 31 | 0 | 5 | 36 | -| [configs/ddpg/classic_control/Pendulum-v1.yaml](/configs/ddpg/classic_control/Pendulum-v1.yaml) | YAML | 31 | 0 | 5 | 36 | -| [configs/ddpg/mujoco.yaml](/configs/ddpg/mujoco.yaml) | YAML | 31 | 0 | 6 | 37 | -| [configs/ddqn/atari.yaml](/configs/ddqn/atari.yaml) | YAML | 38 | 1 | 7 | 46 | -| [configs/ddqn/box2d/CarRacing-v2.yaml](/configs/ddqn/box2d/CarRacing-v2.yaml) | YAML | 32 | 1 | 7 | 40 | -| [configs/ddqn/box2d/LunarLander-v2.yaml](/configs/ddqn/box2d/LunarLander-v2.yaml) | YAML | 30 | 0 | 6 | 36 | -| [configs/ddqn/classic_control/Acrobot-v1.yaml](/configs/ddqn/classic_control/Acrobot-v1.yaml) | YAML | 30 | 0 | 7 | 37 | -| [configs/ddqn/classic_control/CartPole-v1.yaml](/configs/ddqn/classic_control/CartPole-v1.yaml) | YAML | 30 | 0 | 7 | 37 | -| [configs/ddqn/classic_control/MountainCar-v0.yaml](/configs/ddqn/classic_control/MountainCar-v0.yaml) | YAML | 30 | 0 | 7 | 37 | -| [configs/dqn/atari.yaml](/configs/dqn/atari.yaml) | YAML | 38 | 1 | 7 | 46 | -| [configs/dqn/box2d/CarRacing-v2.yaml](/configs/dqn/box2d/CarRacing-v2.yaml) | YAML | 32 | 1 | 7 | 40 | -| [configs/dqn/box2d/LunarLander-v2.yaml](/configs/dqn/box2d/LunarLander-v2.yaml) | YAML | 30 | 0 | 6 | 36 | -| [configs/dqn/classic_control/Acrobot-v1.yaml](/configs/dqn/classic_control/Acrobot-v1.yaml) | YAML | 30 | 0 | 6 | 36 | -| [configs/dqn/classic_control/CartPole-v1.yaml](/configs/dqn/classic_control/CartPole-v1.yaml) | YAML | 30 | 0 | 6 | 36 | -| [configs/dqn/classic_control/MountainCar-v0.yaml](/configs/dqn/classic_control/MountainCar-v0.yaml) | YAML | 29 | 0 | 6 | 35 | -| [configs/drqn/atari.yaml](/configs/drqn/atari.yaml) | YAML | 42 | 1 | 7 | 50 | -| [configs/drqn/box2d/CarRacing-v2.yaml](/configs/drqn/box2d/CarRacing-v2.yaml) | YAML | 36 | 1 | 7 | 44 | -| [configs/drqn/box2d/LunarLander-v2.yaml](/configs/drqn/box2d/LunarLander-v2.yaml) | YAML | 34 | 0 | 6 | 40 | -| [configs/drqn/classic_control/Acrobot-v1.yaml](/configs/drqn/classic_control/Acrobot-v1.yaml) | YAML | 34 | 0 | 6 | 40 | -| [configs/drqn/classic_control/CartPole-v1.yaml](/configs/drqn/classic_control/CartPole-v1.yaml) | YAML | 34 | 0 | 6 | 40 | -| [configs/drqn/classic_control/MountainCar-v0.yaml](/configs/drqn/classic_control/MountainCar-v0.yaml) | YAML | 33 | 0 | 6 | 39 | -| [configs/dueldqn/atari.yaml](/configs/dueldqn/atari.yaml) | YAML | 38 | 1 | 7 | 46 | -| [configs/dueldqn/box2d/CarRacing-v2.yaml](/configs/dueldqn/box2d/CarRacing-v2.yaml) | YAML | 32 | 1 | 7 | 40 | -| [configs/dueldqn/box2d/LunarLander-v2.yaml](/configs/dueldqn/box2d/LunarLander-v2.yaml) | YAML | 30 | 0 | 6 | 36 | -| [configs/dueldqn/classic_control/Acrobot-v1.yaml](/configs/dueldqn/classic_control/Acrobot-v1.yaml) | YAML | 30 | 0 | 6 | 36 | -| [configs/dueldqn/classic_control/CartPole-v1.yaml](/configs/dueldqn/classic_control/CartPole-v1.yaml) | YAML | 30 | 0 | 6 | 36 | -| [configs/dueldqn/classic_control/MountainCar-v0.yaml](/configs/dueldqn/classic_control/MountainCar-v0.yaml) | YAML | 30 | 0 | 6 | 36 | -| [configs/iddpg/mpe/simple_adversary_v3.yaml](/configs/iddpg/mpe/simple_adversary_v3.yaml) | YAML | 27 | 0 | 7 | 34 | -| [configs/iddpg/mpe/simple_push_v3.yaml](/configs/iddpg/mpe/simple_push_v3.yaml) | YAML | 25 | 0 | 7 | 32 | -| [configs/iddpg/mpe/simple_spread_v3.yaml](/configs/iddpg/mpe/simple_spread_v3.yaml) | YAML | 25 | 0 | 7 | 32 | -| [configs/ippo/mpe/simple_spread_v3.yaml](/configs/ippo/mpe/simple_spread_v3.yaml) | YAML | 44 | 1 | 7 | 52 | -| [configs/ippo/sc2/2m_vs_1z.yaml](/configs/ippo/sc2/2m_vs_1z.yaml) | YAML | 55 | 2 | 8 | 65 | -| [configs/ippo/sc2/3m.yaml](/configs/ippo/sc2/3m.yaml) | YAML | 55 | 2 | 8 | 65 | -| [configs/iql/football/3v1.yaml](/configs/iql/football/3v1.yaml) | YAML | 49 | 2 | 7 | 58 | -| [configs/iql/mpe/simple_spread_v3.yaml](/configs/iql/mpe/simple_spread_v3.yaml) | YAML | 35 | 0 | 6 | 41 | -| [configs/iql/sc2/25m.yaml](/configs/iql/sc2/25m.yaml) | YAML | 40 | 1 | 7 | 48 | -| [configs/iql/sc2/2m_vs_1z.yaml](/configs/iql/sc2/2m_vs_1z.yaml) | YAML | 41 | 1 | 7 | 49 | -| [configs/iql/sc2/3m.yaml](/configs/iql/sc2/3m.yaml) | YAML | 40 | 1 | 7 | 48 | -| [configs/iql/sc2/5m_vs_6m.yaml](/configs/iql/sc2/5m_vs_6m.yaml) | YAML | 40 | 1 | 7 | 48 | -| [configs/iql/sc2/8m.yaml](/configs/iql/sc2/8m.yaml) | YAML | 40 | 1 | 7 | 48 | -| [configs/iql/sc2/8m_vs_9m.yaml](/configs/iql/sc2/8m_vs_9m.yaml) | YAML | 40 | 1 | 7 | 48 | -| [configs/iql/sc2/MMM2.yaml](/configs/iql/sc2/MMM2.yaml) | YAML | 40 | 1 | 7 | 48 | -| [configs/iql/sc2/corridor.yaml](/configs/iql/sc2/corridor.yaml) | YAML | 40 | 1 | 7 | 48 | -| [configs/isac/mpe/simple_adversary_v3.yaml](/configs/isac/mpe/simple_adversary_v3.yaml) | YAML | 26 | 0 | 8 | 34 | -| [configs/isac/mpe/simple_push_v3.yaml](/configs/isac/mpe/simple_push_v3.yaml) | YAML | 26 | 0 | 8 | 34 | -| [configs/isac/mpe/simple_spread_v3.yaml](/configs/isac/mpe/simple_spread_v3.yaml) | YAML | 26 | 0 | 8 | 34 | -| [configs/maddpg/mpe/simple_adversary_v3.yaml](/configs/maddpg/mpe/simple_adversary_v3.yaml) | YAML | 35 | 0 | 5 | 40 | -| [configs/maddpg/mpe/simple_push_v3.yaml](/configs/maddpg/mpe/simple_push_v3.yaml) | YAML | 27 | 0 | 7 | 34 | -| [configs/maddpg/mpe/simple_spread_v3.yaml](/configs/maddpg/mpe/simple_spread_v3.yaml) | YAML | 35 | 0 | 6 | 41 | -| [configs/mappo/mpe/simple_spread_v3.yaml](/configs/mappo/mpe/simple_spread_v3.yaml) | YAML | 45 | 1 | 7 | 53 | -| [configs/mappo/sc2/25m.yaml](/configs/mappo/sc2/25m.yaml) | YAML | 55 | 2 | 8 | 65 | -| [configs/mappo/sc2/2m_vs_1z.yaml](/configs/mappo/sc2/2m_vs_1z.yaml) | YAML | 56 | 2 | 8 | 66 | -| [configs/mappo/sc2/3m.yaml](/configs/mappo/sc2/3m.yaml) | YAML | 55 | 2 | 8 | 65 | -| [configs/mappo/sc2/5m_vs_6m.yaml](/configs/mappo/sc2/5m_vs_6m.yaml) | YAML | 55 | 2 | 8 | 65 | -| [configs/mappo/sc2/8m.yaml](/configs/mappo/sc2/8m.yaml) | YAML | 55 | 2 | 8 | 65 | -| [configs/mappo/sc2/8m_vs_9m.yaml](/configs/mappo/sc2/8m_vs_9m.yaml) | YAML | 55 | 2 | 8 | 65 | -| [configs/mappo/sc2/MMM2.yaml](/configs/mappo/sc2/MMM2.yaml) | YAML | 55 | 2 | 8 | 65 | -| [configs/mappo/sc2/corridor.yaml](/configs/mappo/sc2/corridor.yaml) | YAML | 55 | 2 | 8 | 65 | -| [configs/masac/mpe/simple_push_v3.yaml](/configs/masac/mpe/simple_push_v3.yaml) | YAML | 26 | 0 | 8 | 34 | -| [configs/masac/mpe/simple_spread_v3.yaml](/configs/masac/mpe/simple_spread_v3.yaml) | YAML | 26 | 0 | 8 | 34 | -| [configs/matd3/mpe/simple_push_v3.yaml](/configs/matd3/mpe/simple_push_v3.yaml) | YAML | 25 | 0 | 7 | 32 | -| [configs/matd3/mpe/simple_spread_v3.yaml](/configs/matd3/mpe/simple_spread_v3.yaml) | YAML | 25 | 0 | 7 | 32 | -| [configs/mfac/mpe/simple_spread_v3.yaml](/configs/mfac/mpe/simple_spread_v3.yaml) | YAML | 32 | 1 | 7 | 40 | -| [configs/mfq/magent2/adversarial_pursuit_v4.yaml](/configs/mfq/magent2/adversarial_pursuit_v4.yaml) | YAML | 43 | 1 | 6 | 50 | -| [configs/mfq/mpe/simple_spread_v3.yaml](/configs/mfq/mpe/simple_spread_v3.yaml) | YAML | 25 | 0 | 6 | 31 | -| [configs/mpdqn/Platform.yaml](/configs/mpdqn/Platform.yaml) | YAML | 25 | 0 | 7 | 32 | -| [configs/noisydqn/atari.yaml](/configs/noisydqn/atari.yaml) | YAML | 38 | 1 | 7 | 46 | -| [configs/noisydqn/box2d/CarRacing-v2.yaml](/configs/noisydqn/box2d/CarRacing-v2.yaml) | YAML | 32 | 1 | 7 | 40 | -| [configs/noisydqn/box2d/LunarLander-v2.yaml](/configs/noisydqn/box2d/LunarLander-v2.yaml) | YAML | 30 | 0 | 6 | 36 | -| [configs/noisydqn/classic_control/Acrobot-v1.yaml](/configs/noisydqn/classic_control/Acrobot-v1.yaml) | YAML | 30 | 0 | 6 | 36 | -| [configs/noisydqn/classic_control/CartPole-v1.yaml](/configs/noisydqn/classic_control/CartPole-v1.yaml) | YAML | 30 | 0 | 6 | 36 | -| [configs/noisydqn/classic_control/MountainCar-v0.yaml](/configs/noisydqn/classic_control/MountainCar-v0.yaml) | YAML | 30 | 0 | 6 | 36 | -| [configs/pdqn/Platform.yaml](/configs/pdqn/Platform.yaml) | YAML | 25 | 0 | 7 | 32 | -| [configs/perdqn/atari.yaml](/configs/perdqn/atari.yaml) | YAML | 40 | 1 | 8 | 49 | -| [configs/perdqn/box2d/CarRacing-v2.yaml](/configs/perdqn/box2d/CarRacing-v2.yaml) | YAML | 34 | 1 | 8 | 43 | -| [configs/perdqn/box2d/LunarLander-v2.yaml](/configs/perdqn/box2d/LunarLander-v2.yaml) | YAML | 32 | 0 | 7 | 39 | -| [configs/perdqn/classic_control/Acrobot-v1.yaml](/configs/perdqn/classic_control/Acrobot-v1.yaml) | YAML | 32 | 0 | 7 | 39 | -| [configs/perdqn/classic_control/CartPole-v1.yaml](/configs/perdqn/classic_control/CartPole-v1.yaml) | YAML | 32 | 0 | 7 | 39 | -| [configs/perdqn/classic_control/MountainCar-v1.yaml](/configs/perdqn/classic_control/MountainCar-v1.yaml) | YAML | 32 | 0 | 7 | 39 | -| [configs/pg/box2d/BipedalWalker-v3.yaml](/configs/pg/box2d/BipedalWalker-v3.yaml) | YAML | 31 | 0 | 5 | 36 | -| [configs/pg/box2d/LunarLander-v2.yaml](/configs/pg/box2d/LunarLander-v2.yaml) | YAML | 31 | 0 | 5 | 36 | -| [configs/pg/classic_control/Acrobot-v1.yaml](/configs/pg/classic_control/Acrobot-v1.yaml) | YAML | 31 | 0 | 5 | 36 | -| [configs/pg/classic_control/CartPole-v1.yaml](/configs/pg/classic_control/CartPole-v1.yaml) | YAML | 31 | 0 | 5 | 36 | -| [configs/pg/classic_control/MountainCar-v0.yaml](/configs/pg/classic_control/MountainCar-v0.yaml) | YAML | 31 | 0 | 6 | 37 | -| [configs/pg/classic_control/Pendulum-v1.yaml](/configs/pg/classic_control/Pendulum-v1.yaml) | YAML | 31 | 0 | 5 | 36 | -| [configs/pg/mujoco.yaml](/configs/pg/mujoco.yaml) | YAML | 31 | 0 | 5 | 36 | -| [configs/ppg/box2d/BipedalWalker-v3.yaml](/configs/ppg/box2d/BipedalWalker-v3.yaml) | YAML | 35 | 0 | 6 | 41 | -| [configs/ppg/box2d/LunarLander-v2.yaml](/configs/ppg/box2d/LunarLander-v2.yaml) | YAML | 35 | 0 | 5 | 40 | -| [configs/ppg/classic_control/Acrobot-v1.yaml](/configs/ppg/classic_control/Acrobot-v1.yaml) | YAML | 35 | 0 | 6 | 41 | -| [configs/ppg/classic_control/CartPole-v1.yaml](/configs/ppg/classic_control/CartPole-v1.yaml) | YAML | 35 | 0 | 5 | 40 | -| [configs/ppg/classic_control/MountainCar-v0.yaml](/configs/ppg/classic_control/MountainCar-v0.yaml) | YAML | 35 | 0 | 6 | 41 | -| [configs/ppg/classic_control/Pendulum-v1.yaml](/configs/ppg/classic_control/Pendulum-v1.yaml) | YAML | 35 | 0 | 6 | 41 | -| [configs/ppg/mujoco.yaml](/configs/ppg/mujoco.yaml) | YAML | 35 | 0 | 7 | 42 | -| [configs/ppo/atari.yaml](/configs/ppo/atari.yaml) | YAML | 43 | 1 | 7 | 51 | -| [configs/ppo/box2d/BipedalWalker-v3.yaml](/configs/ppo/box2d/BipedalWalker-v3.yaml) | YAML | 35 | 0 | 6 | 41 | -| [configs/ppo/box2d/CarRacing-v2.yaml](/configs/ppo/box2d/CarRacing-v2.yaml) | YAML | 37 | 1 | 6 | 44 | -| [configs/ppo/box2d/LunarLander-v2.yaml](/configs/ppo/box2d/LunarLander-v2.yaml) | YAML | 35 | 0 | 6 | 41 | -| [configs/ppo/classic_control/Acrobot-v1.yaml](/configs/ppo/classic_control/Acrobot-v1.yaml) | YAML | 35 | 0 | 7 | 42 | -| [configs/ppo/classic_control/CartPole-v1.yaml](/configs/ppo/classic_control/CartPole-v1.yaml) | YAML | 35 | 0 | 7 | 42 | -| [configs/ppo/classic_control/MountainCar-v0.yaml](/configs/ppo/classic_control/MountainCar-v0.yaml) | YAML | 35 | 0 | 7 | 42 | -| [configs/ppo/classic_control/Pendulum-v1.yaml](/configs/ppo/classic_control/Pendulum-v1.yaml) | YAML | 35 | 0 | 7 | 42 | -| [configs/ppo/mujoco.yaml](/configs/ppo/mujoco.yaml) | YAML | 35 | 0 | 7 | 42 | -| [configs/qmix/mpe/simple_spread_v3.yaml](/configs/qmix/mpe/simple_spread_v3.yaml) | YAML | 37 | 0 | 7 | 44 | -| [configs/qmix/sc2/25m.yaml](/configs/qmix/sc2/25m.yaml) | YAML | 43 | 1 | 8 | 52 | -| [configs/qmix/sc2/2m_vs_1z.yaml](/configs/qmix/sc2/2m_vs_1z.yaml) | YAML | 43 | 1 | 8 | 52 | -| [configs/qmix/sc2/3m.yaml](/configs/qmix/sc2/3m.yaml) | YAML | 43 | 1 | 8 | 52 | -| [configs/qmix/sc2/5m_vs_6m.yaml](/configs/qmix/sc2/5m_vs_6m.yaml) | YAML | 43 | 1 | 8 | 52 | -| [configs/qmix/sc2/8m.yaml](/configs/qmix/sc2/8m.yaml) | YAML | 43 | 1 | 8 | 52 | -| [configs/qmix/sc2/8m_vs_9m.yaml](/configs/qmix/sc2/8m_vs_9m.yaml) | YAML | 43 | 1 | 8 | 52 | -| [configs/qmix/sc2/MMM2.yaml](/configs/qmix/sc2/MMM2.yaml) | YAML | 43 | 1 | 8 | 52 | -| [configs/qmix/sc2/corridor.yaml](/configs/qmix/sc2/corridor.yaml) | YAML | 43 | 1 | 8 | 52 | -| [configs/qrdqn/atari.yaml](/configs/qrdqn/atari.yaml) | YAML | 39 | 1 | 7 | 47 | -| [configs/qrdqn/box2d/CarRacing-v2.yaml](/configs/qrdqn/box2d/CarRacing-v2.yaml) | YAML | 33 | 1 | 7 | 41 | -| [configs/qrdqn/box2d/LunarLander-v2.yaml](/configs/qrdqn/box2d/LunarLander-v2.yaml) | YAML | 31 | 0 | 6 | 37 | -| [configs/qrdqn/classic_control/Acrobot-v1.yaml](/configs/qrdqn/classic_control/Acrobot-v1.yaml) | YAML | 31 | 0 | 6 | 37 | -| [configs/qrdqn/classic_control/CartPole-v1.yaml](/configs/qrdqn/classic_control/CartPole-v1.yaml) | YAML | 31 | 0 | 6 | 37 | -| [configs/qrdqn/classic_control/MountainCar-v0.yaml](/configs/qrdqn/classic_control/MountainCar-v0.yaml) | YAML | 31 | 0 | 6 | 37 | -| [configs/qtran/mpe/simple_spread_v3.yaml](/configs/qtran/mpe/simple_spread_v3.yaml) | YAML | 28 | 0 | 6 | 34 | -| [configs/random/mpe/simple_adversary.yaml](/configs/random/mpe/simple_adversary.yaml) | YAML | 7 | 0 | 1 | 8 | -| [configs/random/mpe/simple_push.yaml](/configs/random/mpe/simple_push.yaml) | YAML | 7 | 0 | 1 | 8 | -| [configs/random/mpe/simple_spread.yaml](/configs/random/mpe/simple_spread.yaml) | YAML | 7 | 0 | 1 | 8 | -| [configs/sac/atari.yaml](/configs/sac/atari.yaml) | YAML | 41 | 0 | 6 | 47 | -| [configs/sac/box2d/BipedalWalker-v3.yaml](/configs/sac/box2d/BipedalWalker-v3.yaml) | YAML | 31 | 0 | 6 | 37 | -| [configs/sac/box2d/LunarLander-v2.yaml](/configs/sac/box2d/LunarLander-v2.yaml) | YAML | 32 | 0 | 6 | 38 | -| [configs/sac/classic_control/Acrobot-v1.yaml](/configs/sac/classic_control/Acrobot-v1.yaml) | YAML | 32 | 0 | 6 | 38 | -| [configs/sac/classic_control/CartPole-v1.yaml](/configs/sac/classic_control/CartPole-v1.yaml) | YAML | 32 | 0 | 6 | 38 | -| [configs/sac/classic_control/MountainCar-v0.yaml](/configs/sac/classic_control/MountainCar-v0.yaml) | YAML | 32 | 0 | 6 | 38 | -| [configs/sac/classic_control/Pendulum-v1.yaml](/configs/sac/classic_control/Pendulum-v1.yaml) | YAML | 31 | 0 | 6 | 37 | -| [configs/sac/mujoco.yaml](/configs/sac/mujoco.yaml) | YAML | 33 | 0 | 6 | 39 | -| [configs/spdqn/Platform-v0.yaml](/configs/spdqn/Platform-v0.yaml) | YAML | 25 | 0 | 7 | 32 | -| [configs/td3/box2d/BipedalWalker-v3.yaml](/configs/td3/box2d/BipedalWalker-v3.yaml) | YAML | 31 | 0 | 5 | 36 | -| [configs/td3/classic_control/Pendulum-v1.yaml](/configs/td3/classic_control/Pendulum-v1.yaml) | YAML | 31 | 0 | 5 | 36 | -| [configs/td3/mujoco.yaml](/configs/td3/mujoco.yaml) | YAML | 31 | 0 | 6 | 37 | -| [configs/vdac/mpe/simple_spread_v3.yaml](/configs/vdac/mpe/simple_spread_v3.yaml) | YAML | 41 | 1 | 8 | 50 | -| [configs/vdn/football/3v1.yaml](/configs/vdn/football/3v1.yaml) | YAML | 49 | 2 | 7 | 58 | -| [configs/vdn/mpe/simple_spread_v3.yaml](/configs/vdn/mpe/simple_spread_v3.yaml) | YAML | 35 | 0 | 6 | 41 | -| [configs/vdn/sc2/25m.yaml](/configs/vdn/sc2/25m.yaml) | YAML | 41 | 1 | 7 | 49 | -| [configs/vdn/sc2/2m_vs_1z.yaml](/configs/vdn/sc2/2m_vs_1z.yaml) | YAML | 41 | 1 | 7 | 49 | -| [configs/vdn/sc2/3m.yaml](/configs/vdn/sc2/3m.yaml) | YAML | 41 | 1 | 7 | 49 | -| [configs/vdn/sc2/5m_vs_6m.yaml](/configs/vdn/sc2/5m_vs_6m.yaml) | YAML | 41 | 1 | 7 | 49 | -| [configs/vdn/sc2/8m.yaml](/configs/vdn/sc2/8m.yaml) | YAML | 41 | 1 | 7 | 49 | -| [configs/vdn/sc2/8m_vs_9m.yaml](/configs/vdn/sc2/8m_vs_9m.yaml) | YAML | 41 | 1 | 7 | 49 | -| [configs/vdn/sc2/MMM2.yaml](/configs/vdn/sc2/MMM2.yaml) | YAML | 41 | 1 | 7 | 49 | -| [configs/vdn/sc2/corridor.yaml](/configs/vdn/sc2/corridor.yaml) | YAML | 41 | 1 | 7 | 49 | -| [configs/wqmix/mpe/simple_spread_v3.yaml](/configs/wqmix/mpe/simple_spread_v3.yaml) | YAML | 38 | 0 | 6 | 44 | -| [configs/wqmix/sc2/25m.yaml](/configs/wqmix/sc2/25m.yaml) | YAML | 44 | 1 | 9 | 54 | -| [configs/wqmix/sc2/2m_vs_1z.yaml](/configs/wqmix/sc2/2m_vs_1z.yaml) | YAML | 44 | 1 | 9 | 54 | -| [configs/wqmix/sc2/3m.yaml](/configs/wqmix/sc2/3m.yaml) | YAML | 44 | 1 | 9 | 54 | -| [configs/wqmix/sc2/5m_vs_6m.yaml](/configs/wqmix/sc2/5m_vs_6m.yaml) | YAML | 44 | 1 | 9 | 54 | -| [configs/wqmix/sc2/8m.yaml](/configs/wqmix/sc2/8m.yaml) | YAML | 44 | 1 | 9 | 54 | -| [configs/wqmix/sc2/8m_vs_9m.yaml](/configs/wqmix/sc2/8m_vs_9m.yaml) | YAML | 44 | 1 | 9 | 54 | -| [configs/wqmix/sc2/MMM2.yaml](/configs/wqmix/sc2/MMM2.yaml) | YAML | 44 | 1 | 9 | 54 | -| [configs/wqmix/sc2/corridor.yaml](/configs/wqmix/sc2/corridor.yaml) | YAML | 44 | 1 | 9 | 54 | -| [environment/__init__.py](/environment/__init__.py) | Python | 60 | 0 | 8 | 68 | -| [environment/football/__init__.py](/environment/football/__init__.py) | Python | 20 | 19 | 2 | 41 | -| [environment/football/gfootball_env.py](/environment/football/gfootball_env.py) | Python | 64 | 0 | 10 | 74 | -| [environment/football/gfootball_vec_env.py](/environment/football/gfootball_vec_env.py) | Python | 81 | 0 | 9 | 90 | -| [environment/football/raw_env.py](/environment/football/raw_env.py) | Python | 90 | 2 | 11 | 103 | -| [environment/gym/__init__.py](/environment/gym/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [environment/gym/gym_env.py](/environment/gym/gym_env.py) | Python | 180 | 41 | 33 | 254 | -| [environment/gym/gym_vec_env.py](/environment/gym/gym_vec_env.py) | Python | 196 | 17 | 28 | 241 | -| [environment/magent2/__init__.py](/environment/magent2/__init__.py) | Python | 19 | 1 | 7 | 27 | -| [environment/magent2/build.sh](/environment/magent2/build.sh) | Shell Script | 13 | 3 | 3 | 19 | -| [environment/magent2/builtin/__init__.py](/environment/magent2/builtin/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [environment/magent2/builtin/config/__init__.py](/environment/magent2/builtin/config/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [environment/magent2/builtin/config/battle.py](/environment/magent2/builtin/config/battle.py) | Python | 31 | 2 | 10 | 43 | -| [environment/magent2/builtin/config/double_attack.py](/environment/magent2/builtin/config/double_attack.py) | Python | 41 | 4 | 11 | 56 | -| [environment/magent2/builtin/config/forest.py](/environment/magent2/builtin/config/forest.py) | Python | 41 | 1 | 10 | 52 | -| [environment/magent2/builtin/config/pursuit.py](/environment/magent2/builtin/config/pursuit.py) | Python | 34 | 0 | 10 | 44 | -| [environment/magent2/c_lib.py](/environment/magent2/c_lib.py) | Python | 26 | 5 | 13 | 44 | -| [environment/magent2/environment.py](/environment/magent2/environment.py) | Python | 25 | 4 | 15 | 44 | -| [environment/magent2/environments/__init__.py](/environment/magent2/environments/__init__.py) | Python | 3 | 0 | 3 | 6 | -| [environment/magent2/environments/adversarial_pursuit/__init__.py](/environment/magent2/environments/adversarial_pursuit/__init__.py) | Python | 1 | 0 | 1 | 2 | -| [environment/magent2/environments/adversarial_pursuit/adversarial_pursuit.py](/environment/magent2/environments/adversarial_pursuit/adversarial_pursuit.py) | Python | 130 | 100 | 26 | 256 | -| [environment/magent2/environments/adversarial_pursuit_v4.py](/environment/magent2/environments/adversarial_pursuit_v4.py) | Python | 5 | 0 | 1 | 6 | -| [environment/magent2/environments/battle/__init__.py](/environment/magent2/environments/battle/__init__.py) | Python | 1 | 0 | 1 | 2 | -| [environment/magent2/environments/battle/battle.py](/environment/magent2/environments/battle/battle.py) | Python | 164 | 115 | 27 | 306 | -| [environment/magent2/environments/battle_v4.py](/environment/magent2/environments/battle_v4.py) | Python | 1 | 0 | 1 | 2 | -| [environment/magent2/environments/battlefield/__init__.py](/environment/magent2/environments/battlefield/__init__.py) | Python | 1 | 0 | 1 | 2 | -| [environment/magent2/environments/battlefield/battlefield.py](/environment/magent2/environments/battlefield/battlefield.py) | Python | 146 | 116 | 26 | 288 | -| [environment/magent2/environments/battlefield_v5.py](/environment/magent2/environments/battlefield_v5.py) | Python | 1 | 0 | 1 | 2 | -| [environment/magent2/environments/combined_arms/__init__.py](/environment/magent2/environments/combined_arms/__init__.py) | Python | 1 | 0 | 1 | 2 | -| [environment/magent2/environments/combined_arms/combined_arms.py](/environment/magent2/environments/combined_arms/combined_arms.py) | Python | 259 | 118 | 38 | 415 | -| [environment/magent2/environments/combined_arms_v6.py](/environment/magent2/environments/combined_arms_v6.py) | Python | 1 | 0 | 1 | 2 | -| [environment/magent2/environments/gather/__init__.py](/environment/magent2/environments/gather/__init__.py) | Python | 1 | 0 | 1 | 2 | -| [environment/magent2/environments/gather/gather.py](/environment/magent2/environments/gather/gather.py) | Python | 186 | 105 | 33 | 324 | -| [environment/magent2/environments/gather_v5.py](/environment/magent2/environments/gather_v5.py) | Python | 1 | 0 | 1 | 2 | -| [environment/magent2/environments/magent_env.py](/environment/magent2/environments/magent_env.py) | Python | 247 | 6 | 38 | 291 | -| [environment/magent2/environments/tiger_deer/__init__.py](/environment/magent2/environments/tiger_deer/__init__.py) | Python | 1 | 0 | 1 | 2 | -| [environment/magent2/environments/tiger_deer/tiger_deer.py](/environment/magent2/environments/tiger_deer/tiger_deer.py) | Python | 141 | 88 | 28 | 257 | -| [environment/magent2/environments/tiger_deer_v4.py](/environment/magent2/environments/tiger_deer_v4.py) | Python | 1 | 0 | 1 | 2 | -| [environment/magent2/gridworld.py](/environment/magent2/gridworld.py) | Python | 531 | 287 | 98 | 916 | -| [environment/magent2/magent_env.py](/environment/magent2/magent_env.py) | Python | 58 | 0 | 12 | 70 | -| [environment/magent2/magent_vec_env.py](/environment/magent2/magent_vec_env.py) | Python | 124 | 7 | 23 | 154 | -| [environment/magent2/render.py](/environment/magent2/render.py) | Python | 289 | 2 | 47 | 338 | -| [environment/magent2/utility.py](/environment/magent2/utility.py) | Python | 81 | 16 | 23 | 120 | -| [environment/pettingzoo/__init__.py](/environment/pettingzoo/__init__.py) | Python | 23 | 0 | 2 | 25 | -| [environment/pettingzoo/pettingzoo_env.py](/environment/pettingzoo/pettingzoo_env.py) | Python | 90 | 3 | 17 | 110 | -| [environment/pettingzoo/pettingzoo_vec_env.py](/environment/pettingzoo/pettingzoo_vec_env.py) | Python | 130 | 5 | 22 | 157 | -| [environment/starcraft2/__init__.py](/environment/starcraft2/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [environment/starcraft2/sc2_env.py](/environment/starcraft2/sc2_env.py) | Python | 54 | 0 | 11 | 65 | -| [environment/starcraft2/sc2_vec_env.py](/environment/starcraft2/sc2_vec_env.py) | Python | 261 | 12 | 30 | 303 | -| [environment/vector_envs/__init__.py](/environment/vector_envs/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [environment/vector_envs/env_utils.py](/environment/vector_envs/env_utils.py) | Python | 100 | 11 | 26 | 137 | -| [environment/vector_envs/subproc_vec_env.py](/environment/vector_envs/subproc_vec_env.py) | Python | 132 | 18 | 26 | 176 | -| [environment/vector_envs/vector_env.py](/environment/vector_envs/vector_env.py) | Python | 60 | 28 | 16 | 104 | -| [mindspore/__init__.py](/mindspore/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [mindspore/agents/__init__.py](/mindspore/agents/__init__.py) | Python | 111 | 0 | 6 | 117 | -| [mindspore/agents/agent.py](/mindspore/agents/agent.py) | Python | 39 | 0 | 10 | 49 | -| [mindspore/agents/agents_marl.py](/mindspore/agents/agents_marl.py) | Python | 88 | 0 | 18 | 106 | -| [mindspore/agents/multi_agent_rl/__init__.py](/mindspore/agents/multi_agent_rl/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [mindspore/agents/multi_agent_rl/coma_agents.py](/mindspore/agents/multi_agent_rl/coma_agents.py) | Python | 90 | 1 | 13 | 104 | -| [mindspore/agents/multi_agent_rl/dcg_agents.py](/mindspore/agents/multi_agent_rl/dcg_agents.py) | Python | 86 | 0 | 12 | 98 | -| [mindspore/agents/multi_agent_rl/iddpg_agents.py](/mindspore/agents/multi_agent_rl/iddpg_agents.py) | Python | 80 | 0 | 11 | 91 | -| [mindspore/agents/multi_agent_rl/iql_agents.py](/mindspore/agents/multi_agent_rl/iql_agents.py) | Python | 71 | 0 | 13 | 84 | -| [mindspore/agents/multi_agent_rl/isac_agents.py](/mindspore/agents/multi_agent_rl/isac_agents.py) | Python | 79 | 0 | 11 | 90 | -| [mindspore/agents/multi_agent_rl/maddpg_agents.py](/mindspore/agents/multi_agent_rl/maddpg_agents.py) | Python | 80 | 0 | 11 | 91 | -| [mindspore/agents/multi_agent_rl/mappoclip_agents.py](/mindspore/agents/multi_agent_rl/mappoclip_agents.py) | Python | 83 | 0 | 14 | 97 | -| [mindspore/agents/multi_agent_rl/mappokl_agents.py](/mindspore/agents/multi_agent_rl/mappokl_agents.py) | Python | 84 | 1 | 14 | 99 | -| [mindspore/agents/multi_agent_rl/masac_agents.py](/mindspore/agents/multi_agent_rl/masac_agents.py) | Python | 79 | 0 | 11 | 90 | -| [mindspore/agents/multi_agent_rl/matd3_agents.py](/mindspore/agents/multi_agent_rl/matd3_agents.py) | Python | 84 | 0 | 12 | 96 | -| [mindspore/agents/multi_agent_rl/mfac_agents.py](/mindspore/agents/multi_agent_rl/mfac_agents.py) | Python | 93 | 1 | 16 | 110 | -| [mindspore/agents/multi_agent_rl/mfq_agents.py](/mindspore/agents/multi_agent_rl/mfq_agents.py) | Python | 97 | 0 | 13 | 110 | -| [mindspore/agents/multi_agent_rl/qmix_agents.py](/mindspore/agents/multi_agent_rl/qmix_agents.py) | Python | 73 | 0 | 12 | 85 | -| [mindspore/agents/multi_agent_rl/qtran_agents.py](/mindspore/agents/multi_agent_rl/qtran_agents.py) | Python | 81 | 0 | 13 | 94 | -| [mindspore/agents/multi_agent_rl/vdac_agents.py](/mindspore/agents/multi_agent_rl/vdac_agents.py) | Python | 91 | 0 | 14 | 105 | -| [mindspore/agents/multi_agent_rl/vdn_agents.py](/mindspore/agents/multi_agent_rl/vdn_agents.py) | Python | 72 | 0 | 12 | 84 | -| [mindspore/agents/multi_agent_rl/wqmix_agents.py](/mindspore/agents/multi_agent_rl/wqmix_agents.py) | Python | 76 | 0 | 12 | 88 | -| [mindspore/agents/policy_gradient/__init__.py](/mindspore/agents/policy_gradient/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [mindspore/agents/policy_gradient/a2c_agent.py](/mindspore/agents/policy_gradient/a2c_agent.py) | Python | 128 | 0 | 15 | 143 | -| [mindspore/agents/policy_gradient/ddpg_agent.py](/mindspore/agents/policy_gradient/ddpg_agent.py) | Python | 122 | 0 | 14 | 136 | -| [mindspore/agents/policy_gradient/mpdqn_agent.py](/mindspore/agents/policy_gradient/mpdqn_agent.py) | Python | 165 | 1 | 19 | 185 | -| [mindspore/agents/policy_gradient/pdqn_agent.py](/mindspore/agents/policy_gradient/pdqn_agent.py) | Python | 153 | 1 | 18 | 172 | -| [mindspore/agents/policy_gradient/pg_agent.py](/mindspore/agents/policy_gradient/pg_agent.py) | Python | 125 | 0 | 15 | 140 | -| [mindspore/agents/policy_gradient/ppg_agent.py](/mindspore/agents/policy_gradient/ppg_agent.py) | Python | 145 | 5 | 19 | 169 | -| [mindspore/agents/policy_gradient/ppoclip_agent.py](/mindspore/agents/policy_gradient/ppoclip_agent.py) | Python | 129 | 0 | 17 | 146 | -| [mindspore/agents/policy_gradient/ppokl_agent.py](/mindspore/agents/policy_gradient/ppokl_agent.py) | Python | 129 | 0 | 17 | 146 | -| [mindspore/agents/policy_gradient/sac_agent.py](/mindspore/agents/policy_gradient/sac_agent.py) | Python | 121 | 0 | 17 | 138 | -| [mindspore/agents/policy_gradient/sacdis_agent.py](/mindspore/agents/policy_gradient/sacdis_agent.py) | Python | 120 | 2 | 17 | 139 | -| [mindspore/agents/policy_gradient/spdqn_agent.py](/mindspore/agents/policy_gradient/spdqn_agent.py) | Python | 172 | 1 | 20 | 193 | -| [mindspore/agents/policy_gradient/td3_agent.py](/mindspore/agents/policy_gradient/td3_agent.py) | Python | 123 | 0 | 14 | 137 | -| [mindspore/agents/qlearning_family/C51_agent.py](/mindspore/agents/qlearning_family/C51_agent.py) | Python | 125 | 1 | 20 | 146 | -| [mindspore/agents/qlearning_family/__init__.py](/mindspore/agents/qlearning_family/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [mindspore/agents/qlearning_family/cdqn_agent.py](/mindspore/agents/qlearning_family/cdqn_agent.py) | Python | 125 | 1 | 20 | 146 | -| [mindspore/agents/qlearning_family/cldqn_agent.py](/mindspore/agents/qlearning_family/cldqn_agent.py) | Python | 125 | 1 | 20 | 146 | -| [mindspore/agents/qlearning_family/ddqn_agent.py](/mindspore/agents/qlearning_family/ddqn_agent.py) | Python | 125 | 1 | 20 | 146 | -| [mindspore/agents/qlearning_family/dqn_agent.py](/mindspore/agents/qlearning_family/dqn_agent.py) | Python | 125 | 1 | 20 | 146 | -| [mindspore/agents/qlearning_family/dueldqn_agent.py](/mindspore/agents/qlearning_family/dueldqn_agent.py) | Python | 126 | 1 | 20 | 147 | -| [mindspore/agents/qlearning_family/ldqn_agent.py](/mindspore/agents/qlearning_family/ldqn_agent.py) | Python | 125 | 1 | 20 | 146 | -| [mindspore/agents/qlearning_family/noisydqn_agent.py](/mindspore/agents/qlearning_family/noisydqn_agent.py) | Python | 124 | 1 | 21 | 146 | -| [mindspore/agents/qlearning_family/perdqn_agent.py](/mindspore/agents/qlearning_family/perdqn_agent.py) | Python | 130 | 1 | 22 | 153 | -| [mindspore/agents/qlearning_family/qrdqn_agent.py](/mindspore/agents/qlearning_family/qrdqn_agent.py) | Python | 125 | 1 | 20 | 146 | -| [mindspore/learners/__init__.py](/mindspore/learners/__init__.py) | Python | 49 | 0 | 4 | 53 | -| [mindspore/learners/learner.py](/mindspore/learners/learner.py) | Python | 87 | 1 | 12 | 100 | -| [mindspore/learners/multi_agent_rl/__init__.py](/mindspore/learners/multi_agent_rl/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [mindspore/learners/multi_agent_rl/coma_learner.py](/mindspore/learners/multi_agent_rl/coma_learner.py) | Python | 118 | 9 | 17 | 144 | -| [mindspore/learners/multi_agent_rl/dcg_learner.py](/mindspore/learners/multi_agent_rl/dcg_learner.py) | Python | 138 | 10 | 17 | 165 | -| [mindspore/learners/multi_agent_rl/iddpg_learner.py](/mindspore/learners/multi_agent_rl/iddpg_learner.py) | Python | 75 | 7 | 11 | 93 | -| [mindspore/learners/multi_agent_rl/iql_learner.py](/mindspore/learners/multi_agent_rl/iql_learner.py) | Python | 56 | 8 | 8 | 72 | -| [mindspore/learners/multi_agent_rl/isac_learner.py](/mindspore/learners/multi_agent_rl/isac_learner.py) | Python | 84 | 7 | 13 | 104 | -| [mindspore/learners/multi_agent_rl/maddpg_learner.py](/mindspore/learners/multi_agent_rl/maddpg_learner.py) | Python | 80 | 10 | 10 | 100 | -| [mindspore/learners/multi_agent_rl/mappoclip_learner.py](/mindspore/learners/multi_agent_rl/mappoclip_learner.py) | Python | 77 | 8 | 12 | 97 | -| [mindspore/learners/multi_agent_rl/mappokl_learner.py](/mindspore/learners/multi_agent_rl/mappokl_learner.py) | Python | 82 | 13 | 12 | 107 | -| [mindspore/learners/multi_agent_rl/masac_learner.py](/mindspore/learners/multi_agent_rl/masac_learner.py) | Python | 84 | 7 | 12 | 103 | -| [mindspore/learners/multi_agent_rl/matd3_learner.py](/mindspore/learners/multi_agent_rl/matd3_learner.py) | Python | 104 | 7 | 13 | 124 | -| [mindspore/learners/multi_agent_rl/mfac_learner.py](/mindspore/learners/multi_agent_rl/mfac_learner.py) | Python | 103 | 10 | 14 | 127 | -| [mindspore/learners/multi_agent_rl/mfq_learner.py](/mindspore/learners/multi_agent_rl/mfq_learner.py) | Python | 65 | 7 | 10 | 82 | -| [mindspore/learners/multi_agent_rl/qmix_learner.py](/mindspore/learners/multi_agent_rl/qmix_learner.py) | Python | 61 | 8 | 9 | 78 | -| [mindspore/learners/multi_agent_rl/qtran_learner.py](/mindspore/learners/multi_agent_rl/qtran_learner.py) | Python | 98 | 7 | 14 | 119 | -| [mindspore/learners/multi_agent_rl/vdac_learner.py](/mindspore/learners/multi_agent_rl/vdac_learner.py) | Python | 50 | 6 | 10 | 66 | -| [mindspore/learners/multi_agent_rl/vdn_learner.py](/mindspore/learners/multi_agent_rl/vdn_learner.py) | Python | 60 | 9 | 8 | 77 | -| [mindspore/learners/multi_agent_rl/wqmix_learner.py](/mindspore/learners/multi_agent_rl/wqmix_learner.py) | Python | 84 | 12 | 12 | 108 | -| [mindspore/learners/policy_gradient/__init__.py](/mindspore/learners/policy_gradient/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [mindspore/learners/policy_gradient/a2c_learner.py](/mindspore/learners/policy_gradient/a2c_learner.py) | Python | 46 | 7 | 9 | 62 | -| [mindspore/learners/policy_gradient/ddpg_learner.py](/mindspore/learners/policy_gradient/ddpg_learner.py) | Python | 56 | 2 | 11 | 69 | -| [mindspore/learners/policy_gradient/mpdqn_learner.py](/mindspore/learners/policy_gradient/mpdqn_learner.py) | Python | 81 | 6 | 14 | 101 | -| [mindspore/learners/policy_gradient/pdqn_learner.py](/mindspore/learners/policy_gradient/pdqn_learner.py) | Python | 61 | 6 | 12 | 79 | -| [mindspore/learners/policy_gradient/pg_learner.py](/mindspore/learners/policy_gradient/pg_learner.py) | Python | 40 | 4 | 8 | 52 | -| [mindspore/learners/policy_gradient/ppg_learner.py](/mindspore/learners/policy_gradient/ppg_learner.py) | Python | 79 | 4 | 11 | 94 | -| [mindspore/learners/policy_gradient/ppoclip_learner.py](/mindspore/learners/policy_gradient/ppoclip_learner.py) | Python | 51 | 8 | 7 | 66 | -| [mindspore/learners/policy_gradient/ppokl_learner.py](/mindspore/learners/policy_gradient/ppokl_learner.py) | Python | 51 | 2 | 7 | 60 | -| [mindspore/learners/policy_gradient/sac_learner.py](/mindspore/learners/policy_gradient/sac_learner.py) | Python | 55 | 1 | 12 | 68 | -| [mindspore/learners/policy_gradient/sacdis_learner.py](/mindspore/learners/policy_gradient/sacdis_learner.py) | Python | 61 | 2 | 12 | 75 | -| [mindspore/learners/policy_gradient/spdqn_learner.py](/mindspore/learners/policy_gradient/spdqn_learner.py) | Python | 82 | 6 | 14 | 102 | -| [mindspore/learners/policy_gradient/td3_learner.py](/mindspore/learners/policy_gradient/td3_learner.py) | Python | 60 | 7 | 11 | 78 | -| [mindspore/learners/qlearning_family/__init__.py](/mindspore/learners/qlearning_family/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [mindspore/learners/qlearning_family/c51_learner.py](/mindspore/learners/qlearning_family/c51_learner.py) | Python | 59 | 4 | 15 | 78 | -| [mindspore/learners/qlearning_family/cdqn_learner.py](/mindspore/learners/qlearning_family/cdqn_learner.py) | Python | 45 | 5 | 10 | 60 | -| [mindspore/learners/qlearning_family/cldqn_learner.py](/mindspore/learners/qlearning_family/cldqn_learner.py) | Python | 45 | 5 | 10 | 60 | -| [mindspore/learners/qlearning_family/ddqn_learner.py](/mindspore/learners/qlearning_family/ddqn_learner.py) | Python | 48 | 2 | 11 | 61 | -| [mindspore/learners/qlearning_family/dqn_learner.py](/mindspore/learners/qlearning_family/dqn_learner.py) | Python | 45 | 5 | 10 | 60 | -| [mindspore/learners/qlearning_family/dueldqn_learner.py](/mindspore/learners/qlearning_family/dueldqn_learner.py) | Python | 45 | 2 | 10 | 57 | -| [mindspore/learners/qlearning_family/ldqn_learner.py](/mindspore/learners/qlearning_family/ldqn_learner.py) | Python | 45 | 5 | 10 | 60 | -| [mindspore/learners/qlearning_family/perdqn_learner.py](/mindspore/learners/qlearning_family/perdqn_learner.py) | Python | 50 | 5 | 13 | 68 | -| [mindspore/learners/qlearning_family/qrdqn_learner.py](/mindspore/learners/qlearning_family/qrdqn_learner.py) | Python | 54 | 5 | 11 | 70 | -| [mindspore/policies/__init__.py](/mindspore/policies/__init__.py) | Python | 150 | 3 | 8 | 161 | -| [mindspore/policies/categorical.py](/mindspore/policies/categorical.py) | Python | 201 | 60 | 42 | 303 | -| [mindspore/policies/categorical_marl.py](/mindspore/policies/categorical_marl.py) | Python | 252 | 1 | 39 | 292 | -| [mindspore/policies/deterministic.py](/mindspore/policies/deterministic.py) | Python | 716 | 20 | 108 | 844 | -| [mindspore/policies/deterministic_marl.py](/mindspore/policies/deterministic_marl.py) | Python | 440 | 3 | 70 | 513 | -| [mindspore/policies/gaussian.py](/mindspore/policies/gaussian.py) | Python | 207 | 12 | 35 | 254 | -| [mindspore/policies/gaussian_marl.py](/mindspore/policies/gaussian_marl.py) | Python | 247 | 5 | 43 | 295 | -| [mindspore/policies/mixers.py](/mindspore/policies/mixers.py) | Python | 195 | 8 | 29 | 232 | -| [mindspore/representations/__init__.py](/mindspore/representations/__init__.py) | Python | 35 | 0 | 4 | 39 | -| [mindspore/representations/networks.py](/mindspore/representations/networks.py) | Python | 266 | 5 | 44 | 315 | -| [mindspore/runners/__init__.py](/mindspore/runners/__init__.py) | Python | 7 | 0 | 2 | 9 | -| [mindspore/runners/runner_basic.py](/mindspore/runners/runner_basic.py) | Python | 85 | 2 | 16 | 103 | -| [mindspore/runners/runner_drl.py](/mindspore/runners/runner_drl.py) | Python | 71 | 0 | 8 | 79 | -| [mindspore/runners/runner_marl.py](/mindspore/runners/runner_marl.py) | Python | 105 | 3 | 18 | 126 | -| [mindspore/utils/__init__.py](/mindspore/utils/__init__.py) | Python | 2 | 0 | 0 | 2 | -| [mindspore/utils/distributions.py](/mindspore/utils/distributions.py) | Python | 46 | 0 | 18 | 64 | -| [mindspore/utils/input_reformat.py](/mindspore/utils/input_reformat.py) | Python | 83 | 0 | 11 | 94 | -| [mindspore/utils/layers.py](/mindspore/utils/layers.py) | Python | 90 | 0 | 12 | 102 | -| [mindspore/utils/operations.py](/mindspore/utils/operations.py) | Python | 47 | 0 | 12 | 59 | -| [mindspore/utils/set_trainer.py](/mindspore/utils/set_trainer.py) | Python | 32 | 0 | 7 | 39 | -| [tensorflow/__init__.py](/tensorflow/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [tensorflow/agents/__init__.py](/tensorflow/agents/__init__.py) | Python | 109 | 4 | 9 | 122 | -| [tensorflow/agents/agent.py](/tensorflow/agents/agent.py) | Python | 114 | 6 | 17 | 137 | -| [tensorflow/agents/agents_marl.py](/tensorflow/agents/agents_marl.py) | Python | 83 | 2 | 17 | 102 | -| [tensorflow/agents/multi_agent_rl/__init__.py](/tensorflow/agents/multi_agent_rl/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [tensorflow/agents/multi_agent_rl/coma_agents.py](/tensorflow/agents/multi_agent_rl/coma_agents.py) | Python | 65 | 2 | 10 | 77 | -| [tensorflow/agents/multi_agent_rl/dcg_agents.py](/tensorflow/agents/multi_agent_rl/dcg_agents.py) | Python | 89 | 2 | 12 | 103 | -| [tensorflow/agents/multi_agent_rl/iddpg_agents.py](/tensorflow/agents/multi_agent_rl/iddpg_agents.py) | Python | 82 | 0 | 11 | 93 | -| [tensorflow/agents/multi_agent_rl/iql_agents.py](/tensorflow/agents/multi_agent_rl/iql_agents.py) | Python | 73 | 2 | 11 | 86 | -| [tensorflow/agents/multi_agent_rl/isac_agents.py](/tensorflow/agents/multi_agent_rl/isac_agents.py) | Python | 81 | 0 | 11 | 92 | -| [tensorflow/agents/multi_agent_rl/maddpg_agents.py](/tensorflow/agents/multi_agent_rl/maddpg_agents.py) | Python | 83 | 0 | 11 | 94 | -| [tensorflow/agents/multi_agent_rl/mappoclip_agents.py](/tensorflow/agents/multi_agent_rl/mappoclip_agents.py) | Python | 86 | 0 | 14 | 100 | -| [tensorflow/agents/multi_agent_rl/mappokl_agents.py](/tensorflow/agents/multi_agent_rl/mappokl_agents.py) | Python | 85 | 0 | 14 | 99 | -| [tensorflow/agents/multi_agent_rl/masac_agents.py](/tensorflow/agents/multi_agent_rl/masac_agents.py) | Python | 81 | 0 | 11 | 92 | -| [tensorflow/agents/multi_agent_rl/matd3_agents.py](/tensorflow/agents/multi_agent_rl/matd3_agents.py) | Python | 83 | 0 | 11 | 94 | -| [tensorflow/agents/multi_agent_rl/mfac_agents.py](/tensorflow/agents/multi_agent_rl/mfac_agents.py) | Python | 90 | 0 | 16 | 106 | -| [tensorflow/agents/multi_agent_rl/mfq_agents.py](/tensorflow/agents/multi_agent_rl/mfq_agents.py) | Python | 98 | 0 | 12 | 110 | -| [tensorflow/agents/multi_agent_rl/qmix_agents.py](/tensorflow/agents/multi_agent_rl/qmix_agents.py) | Python | 76 | 2 | 11 | 89 | -| [tensorflow/agents/multi_agent_rl/qtran_agents.py](/tensorflow/agents/multi_agent_rl/qtran_agents.py) | Python | 83 | 2 | 12 | 97 | -| [tensorflow/agents/multi_agent_rl/vdac_agents.py](/tensorflow/agents/multi_agent_rl/vdac_agents.py) | Python | 94 | 0 | 14 | 108 | -| [tensorflow/agents/multi_agent_rl/vdn_agents.py](/tensorflow/agents/multi_agent_rl/vdn_agents.py) | Python | 75 | 2 | 11 | 88 | -| [tensorflow/agents/multi_agent_rl/wqmix_agents.py](/tensorflow/agents/multi_agent_rl/wqmix_agents.py) | Python | 78 | 2 | 11 | 91 | -| [tensorflow/agents/policy_gradient/__init__.py](/tensorflow/agents/policy_gradient/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [tensorflow/agents/policy_gradient/a2c_agent.py](/tensorflow/agents/policy_gradient/a2c_agent.py) | Python | 125 | 1 | 18 | 144 | -| [tensorflow/agents/policy_gradient/ddpg_agent.py](/tensorflow/agents/policy_gradient/ddpg_agent.py) | Python | 111 | 1 | 18 | 130 | -| [tensorflow/agents/policy_gradient/mpdqn_agent.py](/tensorflow/agents/policy_gradient/mpdqn_agent.py) | Python | 161 | 0 | 19 | 180 | -| [tensorflow/agents/policy_gradient/pdqn_agent.py](/tensorflow/agents/policy_gradient/pdqn_agent.py) | Python | 159 | 0 | 19 | 178 | -| [tensorflow/agents/policy_gradient/pg_agent.py](/tensorflow/agents/policy_gradient/pg_agent.py) | Python | 125 | 1 | 19 | 145 | -| [tensorflow/agents/policy_gradient/ppg_agent.py](/tensorflow/agents/policy_gradient/ppg_agent.py) | Python | 128 | 4 | 19 | 151 | -| [tensorflow/agents/policy_gradient/ppoclip_agent.py](/tensorflow/agents/policy_gradient/ppoclip_agent.py) | Python | 127 | 1 | 18 | 146 | -| [tensorflow/agents/policy_gradient/ppokl_agent.py](/tensorflow/agents/policy_gradient/ppokl_agent.py) | Python | 122 | 1 | 18 | 141 | -| [tensorflow/agents/policy_gradient/sac_agent.py](/tensorflow/agents/policy_gradient/sac_agent.py) | Python | 108 | 1 | 19 | 128 | -| [tensorflow/agents/policy_gradient/sacdis_agent.py](/tensorflow/agents/policy_gradient/sacdis_agent.py) | Python | 115 | 2 | 16 | 133 | -| [tensorflow/agents/policy_gradient/spdqn_agent.py](/tensorflow/agents/policy_gradient/spdqn_agent.py) | Python | 165 | 0 | 19 | 184 | -| [tensorflow/agents/policy_gradient/td3_agent.py](/tensorflow/agents/policy_gradient/td3_agent.py) | Python | 112 | 1 | 18 | 131 | -| [tensorflow/agents/qlearning_family/__init__.py](/tensorflow/agents/qlearning_family/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [tensorflow/agents/qlearning_family/c51_agent.py](/tensorflow/agents/qlearning_family/c51_agent.py) | Python | 117 | 2 | 19 | 138 | -| [tensorflow/agents/qlearning_family/ddqn_agent.py](/tensorflow/agents/qlearning_family/ddqn_agent.py) | Python | 117 | 2 | 19 | 138 | -| [tensorflow/agents/qlearning_family/dqn_agent.py](/tensorflow/agents/qlearning_family/dqn_agent.py) | Python | 117 | 2 | 18 | 137 | -| [tensorflow/agents/qlearning_family/drqn_agent.py](/tensorflow/agents/qlearning_family/drqn_agent.py) | Python | 131 | 2 | 18 | 151 | -| [tensorflow/agents/qlearning_family/dueldqn_agent.py](/tensorflow/agents/qlearning_family/dueldqn_agent.py) | Python | 117 | 2 | 19 | 138 | -| [tensorflow/agents/qlearning_family/noisydqn_agent.py](/tensorflow/agents/qlearning_family/noisydqn_agent.py) | Python | 116 | 2 | 19 | 137 | -| [tensorflow/agents/qlearning_family/perdqn_agent.py](/tensorflow/agents/qlearning_family/perdqn_agent.py) | Python | 123 | 2 | 20 | 145 | -| [tensorflow/agents/qlearning_family/qrdqn_agent.py](/tensorflow/agents/qlearning_family/qrdqn_agent.py) | Python | 117 | 2 | 19 | 138 | -| [tensorflow/learners/__init__.py](/tensorflow/learners/__init__.py) | Python | 47 | 0 | 4 | 51 | -| [tensorflow/learners/learner.py](/tensorflow/learners/learner.py) | Python | 66 | 2 | 12 | 80 | -| [tensorflow/learners/multi_agent_rl/__init__.py](/tensorflow/learners/multi_agent_rl/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [tensorflow/learners/multi_agent_rl/coma_learner.py](/tensorflow/learners/multi_agent_rl/coma_learner.py) | Python | 115 | 8 | 17 | 140 | -| [tensorflow/learners/multi_agent_rl/dcg_learner.py](/tensorflow/learners/multi_agent_rl/dcg_learner.py) | Python | 155 | 11 | 20 | 186 | -| [tensorflow/learners/multi_agent_rl/iddpg_learner.py](/tensorflow/learners/multi_agent_rl/iddpg_learner.py) | Python | 77 | 7 | 12 | 96 | -| [tensorflow/learners/multi_agent_rl/iql_learner.py](/tensorflow/learners/multi_agent_rl/iql_learner.py) | Python | 58 | 5 | 12 | 75 | -| [tensorflow/learners/multi_agent_rl/isac_learner.py](/tensorflow/learners/multi_agent_rl/isac_learner.py) | Python | 82 | 5 | 13 | 100 | -| [tensorflow/learners/multi_agent_rl/maddpg_learner.py](/tensorflow/learners/multi_agent_rl/maddpg_learner.py) | Python | 77 | 9 | 12 | 98 | -| [tensorflow/learners/multi_agent_rl/mappoclip_learner.py](/tensorflow/learners/multi_agent_rl/mappoclip_learner.py) | Python | 77 | 7 | 12 | 96 | -| [tensorflow/learners/multi_agent_rl/mappokl_learner.py](/tensorflow/learners/multi_agent_rl/mappokl_learner.py) | Python | 86 | 7 | 14 | 107 | -| [tensorflow/learners/multi_agent_rl/masac_learner.py](/tensorflow/learners/multi_agent_rl/masac_learner.py) | Python | 82 | 5 | 13 | 100 | -| [tensorflow/learners/multi_agent_rl/matd3_learner.py](/tensorflow/learners/multi_agent_rl/matd3_learner.py) | Python | 83 | 6 | 11 | 100 | -| [tensorflow/learners/multi_agent_rl/mfac_learner.py](/tensorflow/learners/multi_agent_rl/mfac_learner.py) | Python | 91 | 11 | 14 | 116 | -| [tensorflow/learners/multi_agent_rl/mfq_learner.py](/tensorflow/learners/multi_agent_rl/mfq_learner.py) | Python | 73 | 8 | 13 | 94 | -| [tensorflow/learners/multi_agent_rl/qmix_learner.py](/tensorflow/learners/multi_agent_rl/qmix_learner.py) | Python | 61 | 7 | 11 | 79 | -| [tensorflow/learners/multi_agent_rl/qtran_learner.py](/tensorflow/learners/multi_agent_rl/qtran_learner.py) | Python | 92 | 8 | 12 | 112 | -| [tensorflow/learners/multi_agent_rl/vdac_learner.py](/tensorflow/learners/multi_agent_rl/vdac_learner.py) | Python | 64 | 6 | 12 | 82 | -| [tensorflow/learners/multi_agent_rl/vdn_learner.py](/tensorflow/learners/multi_agent_rl/vdn_learner.py) | Python | 59 | 6 | 12 | 77 | -| [tensorflow/learners/multi_agent_rl/wqmix_learner.py](/tensorflow/learners/multi_agent_rl/wqmix_learner.py) | Python | 83 | 11 | 14 | 108 | -| [tensorflow/learners/policy_gradient/__init__.py](/tensorflow/learners/policy_gradient/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [tensorflow/learners/policy_gradient/a2c_learner.py](/tensorflow/learners/policy_gradient/a2c_learner.py) | Python | 43 | 0 | 9 | 52 | -| [tensorflow/learners/policy_gradient/ddpg_learner.py](/tensorflow/learners/policy_gradient/ddpg_learner.py) | Python | 63 | 2 | 12 | 77 | -| [tensorflow/learners/policy_gradient/mpdqn_learner.py](/tensorflow/learners/policy_gradient/mpdqn_learner.py) | Python | 68 | 2 | 12 | 82 | -| [tensorflow/learners/policy_gradient/pdqn_learner.py](/tensorflow/learners/policy_gradient/pdqn_learner.py) | Python | 68 | 2 | 12 | 82 | -| [tensorflow/learners/policy_gradient/pg_learner.py](/tensorflow/learners/policy_gradient/pg_learner.py) | Python | 37 | 0 | 11 | 48 | -| [tensorflow/learners/policy_gradient/ppg_learner.py](/tensorflow/learners/policy_gradient/ppg_learner.py) | Python | 95 | 1 | 15 | 111 | -| [tensorflow/learners/policy_gradient/ppoclip_learner.py](/tensorflow/learners/policy_gradient/ppoclip_learner.py) | Python | 47 | 1 | 8 | 56 | -| [tensorflow/learners/policy_gradient/ppokl_learner.py](/tensorflow/learners/policy_gradient/ppokl_learner.py) | Python | 56 | 1 | 9 | 66 | -| [tensorflow/learners/policy_gradient/sac_learner.py](/tensorflow/learners/policy_gradient/sac_learner.py) | Python | 65 | 3 | 12 | 80 | -| [tensorflow/learners/policy_gradient/sacdis_learner.py](/tensorflow/learners/policy_gradient/sacdis_learner.py) | Python | 69 | 3 | 12 | 84 | -| [tensorflow/learners/policy_gradient/spdqn_learner.py](/tensorflow/learners/policy_gradient/spdqn_learner.py) | Python | 72 | 2 | 12 | 86 | -| [tensorflow/learners/policy_gradient/td3_learner.py](/tensorflow/learners/policy_gradient/td3_learner.py) | Python | 63 | 6 | 11 | 80 | -| [tensorflow/learners/qlearning_family/__init__.py](/tensorflow/learners/qlearning_family/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [tensorflow/learners/qlearning_family/c51_learner.py](/tensorflow/learners/qlearning_family/c51_learner.py) | Python | 41 | 0 | 13 | 54 | -| [tensorflow/learners/qlearning_family/cdqn_learner.py](/tensorflow/learners/qlearning_family/cdqn_learner.py) | Python | 38 | 1 | 8 | 47 | -| [tensorflow/learners/qlearning_family/cldqn_learner.py](/tensorflow/learners/qlearning_family/cldqn_learner.py) | Python | 40 | 1 | 8 | 49 | -| [tensorflow/learners/qlearning_family/ddqn_learner.py](/tensorflow/learners/qlearning_family/ddqn_learner.py) | Python | 40 | 1 | 9 | 50 | -| [tensorflow/learners/qlearning_family/dqn_learner.py](/tensorflow/learners/qlearning_family/dqn_learner.py) | Python | 41 | 0 | 8 | 49 | -| [tensorflow/learners/qlearning_family/drqn_learner.py](/tensorflow/learners/qlearning_family/drqn_learner.py) | Python | 44 | 2 | 11 | 57 | -| [tensorflow/learners/qlearning_family/dueldqn_learner.py](/tensorflow/learners/qlearning_family/dueldqn_learner.py) | Python | 39 | 1 | 8 | 48 | -| [tensorflow/learners/qlearning_family/ldqn_learner.py](/tensorflow/learners/qlearning_family/ldqn_learner.py) | Python | 39 | 1 | 8 | 48 | -| [tensorflow/learners/qlearning_family/perdqn_learner.py](/tensorflow/learners/qlearning_family/perdqn_learner.py) | Python | 41 | 1 | 9 | 51 | -| [tensorflow/learners/qlearning_family/qrdqn_learner.py](/tensorflow/learners/qlearning_family/qrdqn_learner.py) | Python | 39 | 1 | 7 | 47 | -| [tensorflow/policies/__init__.py](/tensorflow/policies/__init__.py) | Python | 166 | 3 | 9 | 178 | -| [tensorflow/policies/categorical.py](/tensorflow/policies/categorical.py) | Python | 195 | 3 | 31 | 229 | -| [tensorflow/policies/categorical_marl.py](/tensorflow/policies/categorical_marl.py) | Python | 253 | 1 | 30 | 284 | -| [tensorflow/policies/deterministic.py](/tensorflow/policies/deterministic.py) | Python | 706 | 0 | 97 | 803 | -| [tensorflow/policies/deterministic_marl.py](/tensorflow/policies/deterministic_marl.py) | Python | 680 | 26 | 81 | 787 | -| [tensorflow/policies/gaussian.py](/tensorflow/policies/gaussian.py) | Python | 215 | 2 | 32 | 249 | -| [tensorflow/policies/gaussian_marl.py](/tensorflow/policies/gaussian_marl.py) | Python | 215 | 3 | 29 | 247 | -| [tensorflow/policies/mixers.py](/tensorflow/policies/mixers.py) | Python | 204 | 8 | 32 | 244 | -| [tensorflow/representations/__init__.py](/tensorflow/representations/__init__.py) | Python | 40 | 0 | 5 | 45 | -| [tensorflow/representations/networks.py](/tensorflow/representations/networks.py) | Python | 288 | 1 | 46 | 335 | -| [tensorflow/runners/__init__.py](/tensorflow/runners/__init__.py) | Python | 7 | 0 | 2 | 9 | -| [tensorflow/runners/runner_basic.py](/tensorflow/runners/runner_basic.py) | Python | 126 | 3 | 19 | 148 | -| [tensorflow/runners/runner_drl.py](/tensorflow/runners/runner_drl.py) | Python | 103 | 9 | 16 | 128 | -| [tensorflow/runners/runner_marl.py](/tensorflow/runners/runner_marl.py) | Python | 105 | 3 | 18 | 126 | -| [tensorflow/utils/__init__.py](/tensorflow/utils/__init__.py) | Python | 3 | 0 | 0 | 3 | -| [tensorflow/utils/distributions.py](/tensorflow/utils/distributions.py) | Python | 70 | 0 | 28 | 98 | -| [tensorflow/utils/input_reformat.py](/tensorflow/utils/input_reformat.py) | Python | 82 | 0 | 12 | 94 | -| [tensorflow/utils/layers.py](/tensorflow/utils/layers.py) | Python | 107 | 0 | 13 | 120 | -| [tensorflow/utils/operations.py](/tensorflow/utils/operations.py) | Python | 51 | 3 | 17 | 71 | -| [torch/__init__.py](/torch/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [torch/agents/__init__.py](/torch/agents/__init__.py) | Python | 104 | 0 | 6 | 110 | -| [torch/agents/agent.py](/torch/agents/agent.py) | Python | 115 | 6 | 17 | 138 | -| [torch/agents/agents_marl.py](/torch/agents/agents_marl.py) | Python | 72 | 3 | 15 | 90 | -| [torch/agents/multi_agent_rl/__init__.py](/torch/agents/multi_agent_rl/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [torch/agents/multi_agent_rl/coma_agents.py](/torch/agents/multi_agent_rl/coma_agents.py) | Python | 77 | 4 | 11 | 92 | -| [torch/agents/multi_agent_rl/dcg_agents.py](/torch/agents/multi_agent_rl/dcg_agents.py) | Python | 99 | 0 | 11 | 110 | -| [torch/agents/multi_agent_rl/iddpg_agents.py](/torch/agents/multi_agent_rl/iddpg_agents.py) | Python | 58 | 0 | 6 | 64 | -| [torch/agents/multi_agent_rl/iql_agents.py](/torch/agents/multi_agent_rl/iql_agents.py) | Python | 81 | 0 | 11 | 92 | -| [torch/agents/multi_agent_rl/isac_agents.py](/torch/agents/multi_agent_rl/isac_agents.py) | Python | 57 | 0 | 7 | 64 | -| [torch/agents/multi_agent_rl/maddpg_agents.py](/torch/agents/multi_agent_rl/maddpg_agents.py) | Python | 57 | 0 | 7 | 64 | -| [torch/agents/multi_agent_rl/mappo_agents.py](/torch/agents/multi_agent_rl/mappo_agents.py) | Python | 102 | 4 | 11 | 117 | -| [torch/agents/multi_agent_rl/masac_agents.py](/torch/agents/multi_agent_rl/masac_agents.py) | Python | 57 | 0 | 8 | 65 | -| [torch/agents/multi_agent_rl/matd3_agents.py](/torch/agents/multi_agent_rl/matd3_agents.py) | Python | 61 | 0 | 7 | 68 | -| [torch/agents/multi_agent_rl/mfac_agents.py](/torch/agents/multi_agent_rl/mfac_agents.py) | Python | 73 | 0 | 11 | 84 | -| [torch/agents/multi_agent_rl/mfq_agents.py](/torch/agents/multi_agent_rl/mfq_agents.py) | Python | 77 | 0 | 10 | 87 | -| [torch/agents/multi_agent_rl/qmix_agents.py](/torch/agents/multi_agent_rl/qmix_agents.py) | Python | 84 | 0 | 11 | 95 | -| [torch/agents/multi_agent_rl/qtran_agents.py](/torch/agents/multi_agent_rl/qtran_agents.py) | Python | 58 | 0 | 9 | 67 | -| [torch/agents/multi_agent_rl/vdac_agents.py](/torch/agents/multi_agent_rl/vdac_agents.py) | Python | 69 | 0 | 10 | 79 | -| [torch/agents/multi_agent_rl/vdn_agents.py](/torch/agents/multi_agent_rl/vdn_agents.py) | Python | 83 | 0 | 11 | 94 | -| [torch/agents/multi_agent_rl/wqmix_agents.py](/torch/agents/multi_agent_rl/wqmix_agents.py) | Python | 86 | 0 | 11 | 97 | -| [torch/agents/policy_gradient/__init__.py](/torch/agents/policy_gradient/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [torch/agents/policy_gradient/a2c_agent.py](/torch/agents/policy_gradient/a2c_agent.py) | Python | 144 | 1 | 17 | 162 | -| [torch/agents/policy_gradient/ddpg_agent.py](/torch/agents/policy_gradient/ddpg_agent.py) | Python | 116 | 1 | 18 | 135 | -| [torch/agents/policy_gradient/mpdqn_agent.py](/torch/agents/policy_gradient/mpdqn_agent.py) | Python | 159 | 0 | 19 | 178 | -| [torch/agents/policy_gradient/pdqn_agent.py](/torch/agents/policy_gradient/pdqn_agent.py) | Python | 158 | 0 | 20 | 178 | -| [torch/agents/policy_gradient/pg_agent.py](/torch/agents/policy_gradient/pg_agent.py) | Python | 134 | 1 | 15 | 150 | -| [torch/agents/policy_gradient/ppg_agent.py](/torch/agents/policy_gradient/ppg_agent.py) | Python | 149 | 4 | 18 | 171 | -| [torch/agents/policy_gradient/ppoclip_agent.py](/torch/agents/policy_gradient/ppoclip_agent.py) | Python | 148 | 1 | 19 | 168 | -| [torch/agents/policy_gradient/ppokl_agent.py](/torch/agents/policy_gradient/ppokl_agent.py) | Python | 146 | 1 | 18 | 165 | -| [torch/agents/policy_gradient/sac_agent.py](/torch/agents/policy_gradient/sac_agent.py) | Python | 112 | 1 | 19 | 132 | -| [torch/agents/policy_gradient/sacdis_agent.py](/torch/agents/policy_gradient/sacdis_agent.py) | Python | 119 | 1 | 16 | 136 | -| [torch/agents/policy_gradient/spdqn_agent.py](/torch/agents/policy_gradient/spdqn_agent.py) | Python | 157 | 0 | 19 | 176 | -| [torch/agents/policy_gradient/td3_agent.py](/torch/agents/policy_gradient/td3_agent.py) | Python | 116 | 1 | 18 | 135 | -| [torch/agents/qlearning_family/__init__.py](/torch/agents/qlearning_family/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [torch/agents/qlearning_family/c51_agent.py](/torch/agents/qlearning_family/c51_agent.py) | Python | 121 | 2 | 19 | 142 | -| [torch/agents/qlearning_family/ddqn_agent.py](/torch/agents/qlearning_family/ddqn_agent.py) | Python | 122 | 2 | 18 | 142 | -| [torch/agents/qlearning_family/dqn_agent.py](/torch/agents/qlearning_family/dqn_agent.py) | Python | 121 | 2 | 18 | 141 | -| [torch/agents/qlearning_family/drqn_agent.py](/torch/agents/qlearning_family/drqn_agent.py) | Python | 138 | 2 | 20 | 160 | -| [torch/agents/qlearning_family/dueldqn_agent.py](/torch/agents/qlearning_family/dueldqn_agent.py) | Python | 122 | 2 | 19 | 143 | -| [torch/agents/qlearning_family/noisydqn_agent.py](/torch/agents/qlearning_family/noisydqn_agent.py) | Python | 122 | 2 | 19 | 143 | -| [torch/agents/qlearning_family/perdqn_agent.py](/torch/agents/qlearning_family/perdqn_agent.py) | Python | 128 | 2 | 20 | 150 | -| [torch/agents/qlearning_family/qrdqn_agent.py](/torch/agents/qlearning_family/qrdqn_agent.py) | Python | 122 | 2 | 19 | 143 | -| [torch/learners/__init__.py](/torch/learners/__init__.py) | Python | 43 | 1 | 4 | 48 | -| [torch/learners/learner.py](/torch/learners/learner.py) | Python | 79 | 0 | 17 | 96 | -| [torch/learners/multi_agent_rl/__init__.py](/torch/learners/multi_agent_rl/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [torch/learners/multi_agent_rl/coma_learner.py](/torch/learners/multi_agent_rl/coma_learner.py) | Python | 98 | 8 | 16 | 122 | -| [torch/learners/multi_agent_rl/dcg_learner.py](/torch/learners/multi_agent_rl/dcg_learner.py) | Python | 188 | 8 | 22 | 218 | -| [torch/learners/multi_agent_rl/iddpg_learner.py](/torch/learners/multi_agent_rl/iddpg_learner.py) | Python | 64 | 5 | 11 | 80 | -| [torch/learners/multi_agent_rl/iql_learner.py](/torch/learners/multi_agent_rl/iql_learner.py) | Python | 104 | 9 | 21 | 134 | -| [torch/learners/multi_agent_rl/isac_learner.py](/torch/learners/multi_agent_rl/isac_learner.py) | Python | 70 | 6 | 11 | 87 | -| [torch/learners/multi_agent_rl/maddpg_learner.py](/torch/learners/multi_agent_rl/maddpg_learner.py) | Python | 67 | 9 | 10 | 86 | -| [torch/learners/multi_agent_rl/mappo_learner.py](/torch/learners/multi_agent_rl/mappo_learner.py) | Python | 178 | 14 | 20 | 212 | -| [torch/learners/multi_agent_rl/masac_learner.py](/torch/learners/multi_agent_rl/masac_learner.py) | Python | 70 | 6 | 11 | 87 | -| [torch/learners/multi_agent_rl/matd3_learner.py](/torch/learners/multi_agent_rl/matd3_learner.py) | Python | 76 | 6 | 9 | 91 | -| [torch/learners/multi_agent_rl/mfac_learner.py](/torch/learners/multi_agent_rl/mfac_learner.py) | Python | 80 | 10 | 13 | 103 | -| [torch/learners/multi_agent_rl/mfq_learner.py](/torch/learners/multi_agent_rl/mfq_learner.py) | Python | 57 | 7 | 11 | 75 | -| [torch/learners/multi_agent_rl/qmix_learner.py](/torch/learners/multi_agent_rl/qmix_learner.py) | Python | 111 | 11 | 18 | 140 | -| [torch/learners/multi_agent_rl/qtran_learner.py](/torch/learners/multi_agent_rl/qtran_learner.py) | Python | 84 | 8 | 11 | 103 | -| [torch/learners/multi_agent_rl/vdac_learner.py](/torch/learners/multi_agent_rl/vdac_learner.py) | Python | 50 | 6 | 10 | 66 | -| [torch/learners/multi_agent_rl/vdn_learner.py](/torch/learners/multi_agent_rl/vdn_learner.py) | Python | 108 | 14 | 18 | 140 | -| [torch/learners/multi_agent_rl/wqmix_learner.py](/torch/learners/multi_agent_rl/wqmix_learner.py) | Python | 168 | 19 | 23 | 210 | -| [torch/learners/policy_gradient/__init__.py](/torch/learners/policy_gradient/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [torch/learners/policy_gradient/a2c_learner.py](/torch/learners/policy_gradient/a2c_learner.py) | Python | 41 | 1 | 9 | 51 | -| [torch/learners/policy_gradient/ddpg_learner.py](/torch/learners/policy_gradient/ddpg_learner.py) | Python | 44 | 3 | 10 | 57 | -| [torch/learners/policy_gradient/mpdqn_learner.py](/torch/learners/policy_gradient/mpdqn_learner.py) | Python | 46 | 2 | 12 | 60 | -| [torch/learners/policy_gradient/pdqn_learner.py](/torch/learners/policy_gradient/pdqn_learner.py) | Python | 46 | 2 | 19 | 67 | -| [torch/learners/policy_gradient/pg_learner.py](/torch/learners/policy_gradient/pg_learner.py) | Python | 35 | 1 | 9 | 45 | -| [torch/learners/policy_gradient/ppg_learner.py](/torch/learners/policy_gradient/ppg_learner.py) | Python | 78 | 2 | 11 | 91 | -| [torch/learners/policy_gradient/ppoclip_learner.py](/torch/learners/policy_gradient/ppoclip_learner.py) | Python | 54 | 2 | 10 | 66 | -| [torch/learners/policy_gradient/ppokl_learner.py](/torch/learners/policy_gradient/ppokl_learner.py) | Python | 52 | 2 | 9 | 63 | -| [torch/learners/policy_gradient/sac_learner.py](/torch/learners/policy_gradient/sac_learner.py) | Python | 44 | 3 | 10 | 57 | -| [torch/learners/policy_gradient/sacdis_learner.py](/torch/learners/policy_gradient/sacdis_learner.py) | Python | 50 | 5 | 10 | 65 | -| [torch/learners/policy_gradient/spdqn_learner.py](/torch/learners/policy_gradient/spdqn_learner.py) | Python | 46 | 2 | 12 | 60 | -| [torch/learners/policy_gradient/td3_learner.py](/torch/learners/policy_gradient/td3_learner.py) | Python | 49 | 6 | 9 | 64 | -| [torch/learners/qlearning_family/__init__.py](/torch/learners/qlearning_family/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [torch/learners/qlearning_family/c51_learner.py](/torch/learners/qlearning_family/c51_learner.py) | Python | 41 | 1 | 9 | 51 | -| [torch/learners/qlearning_family/ddqn_learner.py](/torch/learners/qlearning_family/ddqn_learner.py) | Python | 39 | 1 | 11 | 51 | -| [torch/learners/qlearning_family/dqn_learner.py](/torch/learners/qlearning_family/dqn_learner.py) | Python | 38 | 1 | 9 | 48 | -| [torch/learners/qlearning_family/drqn_learner.py](/torch/learners/qlearning_family/drqn_learner.py) | Python | 42 | 2 | 11 | 55 | -| [torch/learners/qlearning_family/dueldqn_learner.py](/torch/learners/qlearning_family/dueldqn_learner.py) | Python | 38 | 1 | 9 | 48 | -| [torch/learners/qlearning_family/perdqn_learner.py](/torch/learners/qlearning_family/perdqn_learner.py) | Python | 39 | 1 | 9 | 49 | -| [torch/learners/qlearning_family/qrdqn_learner.py](/torch/learners/qlearning_family/qrdqn_learner.py) | Python | 37 | 1 | 8 | 46 | -| [torch/learners/ssl_rl/__init__.py](/torch/learners/ssl_rl/__init__.py) | Python | 0 | 0 | 1 | 1 | -| [torch/learners/ssl_rl/curl_learner.py](/torch/learners/ssl_rl/curl_learner.py) | Python | 0 | 0 | 1 | 1 | -| [torch/policies/__init__.py](/torch/policies/__init__.py) | Python | 159 | 3 | 8 | 170 | -| [torch/policies/categorical.py](/torch/policies/categorical.py) | Python | 208 | 7 | 34 | 249 | -| [torch/policies/categorical_marl.py](/torch/policies/categorical_marl.py) | Python | 222 | 6 | 28 | 256 | -| [torch/policies/coordination_graph.py](/torch/policies/coordination_graph.py) | Python | 68 | 1 | 9 | 78 | -| [torch/policies/deterministic.py](/torch/policies/deterministic.py) | Python | 743 | 2 | 97 | 842 | -| [torch/policies/deterministic_marl.py](/torch/policies/deterministic_marl.py) | Python | 504 | 4 | 64 | 572 | -| [torch/policies/gaussian.py](/torch/policies/gaussian.py) | Python | 217 | 2 | 31 | 250 | -| [torch/policies/gaussian_marl.py](/torch/policies/gaussian_marl.py) | Python | 188 | 4 | 31 | 223 | -| [torch/policies/mixers.py](/torch/policies/mixers.py) | Python | 117 | 6 | 19 | 142 | -| [torch/representations/__init__.py](/torch/representations/__init__.py) | Python | 38 | 0 | 6 | 44 | -| [torch/representations/cnn.py](/torch/representations/cnn.py) | Python | 83 | 1 | 10 | 94 | -| [torch/representations/mlp.py](/torch/representations/mlp.py) | Python | 42 | 2 | 8 | 52 | -| [torch/representations/rnn.py](/torch/representations/rnn.py) | Python | 71 | 0 | 8 | 79 | -| [torch/runners/__init__.py](/torch/runners/__init__.py) | Python | 13 | 0 | 2 | 15 | -| [torch/runners/runner_basic.py](/torch/runners/runner_basic.py) | Python | 11 | 2 | 6 | 19 | -| [torch/runners/runner_drl.py](/torch/runners/runner_drl.py) | Python | 119 | 3 | 14 | 136 | -| [torch/runners/runner_football.py](/torch/runners/runner_football.py) | Python | 102 | 5 | 18 | 125 | -| [torch/runners/runner_magent.py](/torch/runners/runner_magent.py) | Python | 5 | 0 | 3 | 8 | -| [torch/runners/runner_pettingzoo.py](/torch/runners/runner_pettingzoo.py) | Python | 339 | 11 | 43 | 393 | -| [torch/runners/runner_sc2.py](/torch/runners/runner_sc2.py) | Python | 319 | 13 | 39 | 371 | -| [torch/utils/__init__.py](/torch/utils/__init__.py) | Python | 22 | 0 | 4 | 26 | -| [torch/utils/distributions.py](/torch/utils/distributions.py) | Python | 72 | 0 | 29 | 101 | -| [torch/utils/input_reformat.py](/torch/utils/input_reformat.py) | Python | 104 | 0 | 15 | 119 | -| [torch/utils/layers.py](/torch/utils/layers.py) | Python | 101 | 0 | 12 | 113 | -| [torch/utils/operations.py](/torch/utils/operations.py) | Python | 86 | 0 | 18 | 104 | -| [torch/utils/value_norm.py](/torch/utils/value_norm.py) | Python | 54 | 3 | 20 | 77 | - -[Summary](results.md) / Details / [Diff Summary](diff.md) / [Diff Details](diff-details.md) \ No newline at end of file diff --git a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/diff-details.md b/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/diff-details.md deleted file mode 100644 index 8f0988773..000000000 --- a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/diff-details.md +++ /dev/null @@ -1,15 +0,0 @@ -# Diff Details - -Date : 2023-08-23 15:10:05 - -Directory /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy - -Total : 0 files, 0 codes, 0 comments, 0 blanks, all 0 lines - -[Summary](results.md) / [Details](details.md) / [Diff Summary](diff.md) / Diff Details - -## Files -| filename | language | code | comment | blank | total | -| :--- | :--- | ---: | ---: | ---: | ---: | - -[Summary](results.md) / [Details](details.md) / [Diff Summary](diff.md) / Diff Details \ No newline at end of file diff --git a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/diff.csv b/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/diff.csv deleted file mode 100644 index b7d8d7591..000000000 --- a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/diff.csv +++ /dev/null @@ -1,2 +0,0 @@ -"filename", "language", "", "comment", "blank", "total" -"Total", "-", , 0, 0, 0 \ No newline at end of file diff --git a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/diff.md b/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/diff.md deleted file mode 100644 index eb2cbc01f..000000000 --- a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/diff.md +++ /dev/null @@ -1,19 +0,0 @@ -# Diff Summary - -Date : 2023-08-23 15:10:05 - -Directory /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy - -Total : 0 files, 0 codes, 0 comments, 0 blanks, all 0 lines - -[Summary](results.md) / [Details](details.md) / Diff Summary / [Diff Details](diff-details.md) - -## Languages -| language | files | code | comment | blank | total | -| :--- | ---: | ---: | ---: | ---: | ---: | - -## Directories -| path | files | code | comment | blank | total | -| :--- | ---: | ---: | ---: | ---: | ---: | - -[Summary](results.md) / [Details](details.md) / Diff Summary / [Diff Details](diff-details.md) \ No newline at end of file diff --git a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/diff.txt b/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/diff.txt deleted file mode 100644 index c536cf7c7..000000000 --- a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/diff.txt +++ /dev/null @@ -1,22 +0,0 @@ -Date : 2023-08-23 15:10:05 -Directory : /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy -Total : 0 files, 0 codes, 0 comments, 0 blanks, all 0 lines - -Languages -+----------+------------+------------+------------+------------+------------+ -| language | files | code | comment | blank | total | -+----------+------------+------------+------------+------------+------------+ -+----------+------------+------------+------------+------------+------------+ - -Directories -+------+------------+------------+------------+------------+------------+ -| path | files | code | comment | blank | total | -+------+------------+------------+------------+------------+------------+ -+------+------------+------------+------------+------------+------------+ - -Files -+----------+----------+------------+------------+------------+------------+ -| filename | language | code | comment | blank | total | -+----------+----------+------------+------------+------------+------------+ -| Total | | 0 | 0 | 0 | 0 | -+----------+----------+------------+------------+------------+------------+ \ No newline at end of file diff --git a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/results.csv b/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/results.csv deleted file mode 100644 index b8d4f9a48..000000000 --- a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/results.csv +++ /dev/null @@ -1,568 +0,0 @@ -"filename", "language", "Python", "Shell Script", "YAML", "comment", "blank", "total" -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/__init__.py", "Python", 4, 0, 0, 0, 1, 5 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/__init__.py", "Python", 5, 0, 0, 0, 1, 6 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/common_tools.py", "Python", 151, 0, 0, 18, 29, 198 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/memory_tools.py", "Python", 397, 0, 0, 91, 70, 558 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/memory_tools_marl.py", "Python", 377, 0, 0, 106, 61, 544 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/segtree_tool.py", "Python", 69, 0, 0, 3, 15, 87 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/statistic_tools.py", "Python", 115, 0, 0, 0, 13, 128 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/atari.yaml", "YAML", 0, 0, 41, 1, 6, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/box2d/BipedalWalker-v3.yaml", "YAML", 0, 0, 32, 0, 6, 38 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 32, 0, 6, 38 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 33, 0, 6, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 33, 0, 6, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/classic_control/MountainCar-v0.yaml", "YAML", 0, 0, 33, 0, 6, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/classic_control/Pendulum-v1.yaml", "YAML", 0, 0, 33, 0, 6, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/mujoco.yaml", "YAML", 0, 0, 33, 0, 6, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/basic.yaml", "YAML", 0, 0, 13, 3, 6, 22 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/atari.yaml", "YAML", 0, 0, 41, 1, 7, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/box2d/CarRacing-v2.yaml", "YAML", 0, 0, 35, 1, 7, 43 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 33, 0, 6, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 33, 0, 6, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 33, 0, 6, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/classic_control/MountainCar-v0.yaml", "YAML", 0, 0, 33, 0, 6, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/coma/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 38, 0, 7, 45 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 44, 0, 8, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/25m.yaml", "YAML", 0, 0, 49, 1, 8, 58 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/2m_vs_1z.yaml", "YAML", 0, 0, 49, 1, 8, 58 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/3m.yaml", "YAML", 0, 0, 49, 1, 8, 58 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/5m_vs_6m.yaml", "YAML", 0, 0, 49, 1, 8, 58 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/8m.yaml", "YAML", 0, 0, 49, 1, 8, 58 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/8m_vs_9m.yaml", "YAML", 0, 0, 49, 1, 8, 58 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/MMM2.yaml", "YAML", 0, 0, 49, 1, 8, 58 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/corridor.yaml", "YAML", 0, 0, 49, 1, 8, 58 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddpg/box2d/BipedalWalker-v3.yaml", "YAML", 0, 0, 31, 0, 5, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddpg/classic_control/Pendulum-v1.yaml", "YAML", 0, 0, 31, 0, 5, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddpg/mujoco.yaml", "YAML", 0, 0, 31, 0, 6, 37 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/atari.yaml", "YAML", 0, 0, 38, 1, 7, 46 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/box2d/CarRacing-v2.yaml", "YAML", 0, 0, 32, 1, 7, 40 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 30, 0, 6, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 30, 0, 7, 37 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 30, 0, 7, 37 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/classic_control/MountainCar-v0.yaml", "YAML", 0, 0, 30, 0, 7, 37 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/atari.yaml", "YAML", 0, 0, 38, 1, 7, 46 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/box2d/CarRacing-v2.yaml", "YAML", 0, 0, 32, 1, 7, 40 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 30, 0, 6, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 30, 0, 6, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 30, 0, 6, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/classic_control/MountainCar-v0.yaml", "YAML", 0, 0, 29, 0, 6, 35 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/atari.yaml", "YAML", 0, 0, 42, 1, 7, 50 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/box2d/CarRacing-v2.yaml", "YAML", 0, 0, 36, 1, 7, 44 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 34, 0, 6, 40 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 34, 0, 6, 40 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 34, 0, 6, 40 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/classic_control/MountainCar-v0.yaml", "YAML", 0, 0, 33, 0, 6, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/atari.yaml", "YAML", 0, 0, 38, 1, 7, 46 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/box2d/CarRacing-v2.yaml", "YAML", 0, 0, 32, 1, 7, 40 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 30, 0, 6, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 30, 0, 6, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 30, 0, 6, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/classic_control/MountainCar-v0.yaml", "YAML", 0, 0, 30, 0, 6, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iddpg/mpe/simple_adversary_v3.yaml", "YAML", 0, 0, 27, 0, 7, 34 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iddpg/mpe/simple_push_v3.yaml", "YAML", 0, 0, 25, 0, 7, 32 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iddpg/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 25, 0, 7, 32 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ippo/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 44, 1, 7, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ippo/sc2/2m_vs_1z.yaml", "YAML", 0, 0, 55, 2, 8, 65 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ippo/sc2/3m.yaml", "YAML", 0, 0, 55, 2, 8, 65 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/football/3v1.yaml", "YAML", 0, 0, 49, 2, 7, 58 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 35, 0, 6, 41 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/25m.yaml", "YAML", 0, 0, 40, 1, 7, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/2m_vs_1z.yaml", "YAML", 0, 0, 41, 1, 7, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/3m.yaml", "YAML", 0, 0, 40, 1, 7, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/5m_vs_6m.yaml", "YAML", 0, 0, 40, 1, 7, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/8m.yaml", "YAML", 0, 0, 40, 1, 7, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/8m_vs_9m.yaml", "YAML", 0, 0, 40, 1, 7, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/MMM2.yaml", "YAML", 0, 0, 40, 1, 7, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/corridor.yaml", "YAML", 0, 0, 40, 1, 7, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/isac/mpe/simple_adversary_v3.yaml", "YAML", 0, 0, 26, 0, 8, 34 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/isac/mpe/simple_push_v3.yaml", "YAML", 0, 0, 26, 0, 8, 34 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/isac/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 26, 0, 8, 34 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/maddpg/mpe/simple_adversary_v3.yaml", "YAML", 0, 0, 35, 0, 5, 40 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/maddpg/mpe/simple_push_v3.yaml", "YAML", 0, 0, 27, 0, 7, 34 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/maddpg/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 35, 0, 6, 41 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 45, 1, 7, 53 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/25m.yaml", "YAML", 0, 0, 55, 2, 8, 65 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/2m_vs_1z.yaml", "YAML", 0, 0, 56, 2, 8, 66 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/3m.yaml", "YAML", 0, 0, 55, 2, 8, 65 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/5m_vs_6m.yaml", "YAML", 0, 0, 55, 2, 8, 65 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/8m.yaml", "YAML", 0, 0, 55, 2, 8, 65 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/8m_vs_9m.yaml", "YAML", 0, 0, 55, 2, 8, 65 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/MMM2.yaml", "YAML", 0, 0, 55, 2, 8, 65 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/corridor.yaml", "YAML", 0, 0, 55, 2, 8, 65 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/masac/mpe/simple_push_v3.yaml", "YAML", 0, 0, 26, 0, 8, 34 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/masac/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 26, 0, 8, 34 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/matd3/mpe/simple_push_v3.yaml", "YAML", 0, 0, 25, 0, 7, 32 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/matd3/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 25, 0, 7, 32 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mfac/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 32, 1, 7, 40 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mfq/magent2/adversarial_pursuit_v4.yaml", "YAML", 0, 0, 43, 1, 6, 50 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mfq/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 25, 0, 6, 31 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mpdqn/Platform.yaml", "YAML", 0, 0, 25, 0, 7, 32 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/atari.yaml", "YAML", 0, 0, 38, 1, 7, 46 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/box2d/CarRacing-v2.yaml", "YAML", 0, 0, 32, 1, 7, 40 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 30, 0, 6, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 30, 0, 6, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 30, 0, 6, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/classic_control/MountainCar-v0.yaml", "YAML", 0, 0, 30, 0, 6, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pdqn/Platform.yaml", "YAML", 0, 0, 25, 0, 7, 32 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/atari.yaml", "YAML", 0, 0, 40, 1, 8, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/box2d/CarRacing-v2.yaml", "YAML", 0, 0, 34, 1, 8, 43 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 32, 0, 7, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 32, 0, 7, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 32, 0, 7, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/classic_control/MountainCar-v1.yaml", "YAML", 0, 0, 32, 0, 7, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/box2d/BipedalWalker-v3.yaml", "YAML", 0, 0, 31, 0, 5, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 31, 0, 5, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 31, 0, 5, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 31, 0, 5, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/classic_control/MountainCar-v0.yaml", "YAML", 0, 0, 31, 0, 6, 37 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/classic_control/Pendulum-v1.yaml", "YAML", 0, 0, 31, 0, 5, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/mujoco.yaml", "YAML", 0, 0, 31, 0, 5, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/box2d/BipedalWalker-v3.yaml", "YAML", 0, 0, 35, 0, 6, 41 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 35, 0, 5, 40 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 35, 0, 6, 41 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 35, 0, 5, 40 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/classic_control/MountainCar-v0.yaml", "YAML", 0, 0, 35, 0, 6, 41 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/classic_control/Pendulum-v1.yaml", "YAML", 0, 0, 35, 0, 6, 41 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/mujoco.yaml", "YAML", 0, 0, 35, 0, 7, 42 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/atari.yaml", "YAML", 0, 0, 43, 1, 7, 51 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/box2d/BipedalWalker-v3.yaml", "YAML", 0, 0, 35, 0, 6, 41 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/box2d/CarRacing-v2.yaml", "YAML", 0, 0, 37, 1, 6, 44 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 35, 0, 6, 41 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 35, 0, 7, 42 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 35, 0, 7, 42 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/classic_control/MountainCar-v0.yaml", "YAML", 0, 0, 35, 0, 7, 42 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/classic_control/Pendulum-v1.yaml", "YAML", 0, 0, 35, 0, 7, 42 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/mujoco.yaml", "YAML", 0, 0, 35, 0, 7, 42 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 37, 0, 7, 44 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/25m.yaml", "YAML", 0, 0, 43, 1, 8, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/2m_vs_1z.yaml", "YAML", 0, 0, 43, 1, 8, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/3m.yaml", "YAML", 0, 0, 43, 1, 8, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/5m_vs_6m.yaml", "YAML", 0, 0, 43, 1, 8, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/8m.yaml", "YAML", 0, 0, 43, 1, 8, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/8m_vs_9m.yaml", "YAML", 0, 0, 43, 1, 8, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/MMM2.yaml", "YAML", 0, 0, 43, 1, 8, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/corridor.yaml", "YAML", 0, 0, 43, 1, 8, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/atari.yaml", "YAML", 0, 0, 39, 1, 7, 47 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/box2d/CarRacing-v2.yaml", "YAML", 0, 0, 33, 1, 7, 41 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 31, 0, 6, 37 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 31, 0, 6, 37 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 31, 0, 6, 37 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/classic_control/MountainCar-v0.yaml", "YAML", 0, 0, 31, 0, 6, 37 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qtran/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 28, 0, 6, 34 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/random/mpe/simple_adversary.yaml", "YAML", 0, 0, 7, 0, 1, 8 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/random/mpe/simple_push.yaml", "YAML", 0, 0, 7, 0, 1, 8 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/random/mpe/simple_spread.yaml", "YAML", 0, 0, 7, 0, 1, 8 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/atari.yaml", "YAML", 0, 0, 41, 0, 6, 47 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/box2d/BipedalWalker-v3.yaml", "YAML", 0, 0, 31, 0, 6, 37 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/box2d/LunarLander-v2.yaml", "YAML", 0, 0, 32, 0, 6, 38 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/classic_control/Acrobot-v1.yaml", "YAML", 0, 0, 32, 0, 6, 38 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/classic_control/CartPole-v1.yaml", "YAML", 0, 0, 32, 0, 6, 38 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/classic_control/MountainCar-v0.yaml", "YAML", 0, 0, 32, 0, 6, 38 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/classic_control/Pendulum-v1.yaml", "YAML", 0, 0, 31, 0, 6, 37 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/mujoco.yaml", "YAML", 0, 0, 33, 0, 6, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/spdqn/Platform-v0.yaml", "YAML", 0, 0, 25, 0, 7, 32 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/td3/box2d/BipedalWalker-v3.yaml", "YAML", 0, 0, 31, 0, 5, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/td3/classic_control/Pendulum-v1.yaml", "YAML", 0, 0, 31, 0, 5, 36 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/td3/mujoco.yaml", "YAML", 0, 0, 31, 0, 6, 37 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdac/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 41, 1, 8, 50 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/football/3v1.yaml", "YAML", 0, 0, 49, 2, 7, 58 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 35, 0, 6, 41 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/25m.yaml", "YAML", 0, 0, 41, 1, 7, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/2m_vs_1z.yaml", "YAML", 0, 0, 41, 1, 7, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/3m.yaml", "YAML", 0, 0, 41, 1, 7, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/5m_vs_6m.yaml", "YAML", 0, 0, 41, 1, 7, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/8m.yaml", "YAML", 0, 0, 41, 1, 7, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/8m_vs_9m.yaml", "YAML", 0, 0, 41, 1, 7, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/MMM2.yaml", "YAML", 0, 0, 41, 1, 7, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/corridor.yaml", "YAML", 0, 0, 41, 1, 7, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/mpe/simple_spread_v3.yaml", "YAML", 0, 0, 38, 0, 6, 44 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/25m.yaml", "YAML", 0, 0, 44, 1, 9, 54 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/2m_vs_1z.yaml", "YAML", 0, 0, 44, 1, 9, 54 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/3m.yaml", "YAML", 0, 0, 44, 1, 9, 54 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/5m_vs_6m.yaml", "YAML", 0, 0, 44, 1, 9, 54 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/8m.yaml", "YAML", 0, 0, 44, 1, 9, 54 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/8m_vs_9m.yaml", "YAML", 0, 0, 44, 1, 9, 54 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/MMM2.yaml", "YAML", 0, 0, 44, 1, 9, 54 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/corridor.yaml", "YAML", 0, 0, 44, 1, 9, 54 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/__init__.py", "Python", 60, 0, 0, 0, 8, 68 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/football/__init__.py", "Python", 20, 0, 0, 19, 2, 41 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/football/gfootball_env.py", "Python", 64, 0, 0, 0, 10, 74 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/football/gfootball_vec_env.py", "Python", 81, 0, 0, 0, 9, 90 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/football/raw_env.py", "Python", 90, 0, 0, 2, 11, 103 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/gym/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/gym/gym_env.py", "Python", 180, 0, 0, 41, 33, 254 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/gym/gym_vec_env.py", "Python", 196, 0, 0, 17, 28, 241 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/__init__.py", "Python", 19, 0, 0, 1, 7, 27 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/build.sh", "Shell Script", 0, 13, 0, 3, 3, 19 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/battle.py", "Python", 31, 0, 0, 2, 10, 43 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/double_attack.py", "Python", 41, 0, 0, 4, 11, 56 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/forest.py", "Python", 41, 0, 0, 1, 10, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/pursuit.py", "Python", 34, 0, 0, 0, 10, 44 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/c_lib.py", "Python", 26, 0, 0, 5, 13, 44 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environment.py", "Python", 25, 0, 0, 4, 15, 44 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/__init__.py", "Python", 3, 0, 0, 0, 3, 6 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/adversarial_pursuit/__init__.py", "Python", 1, 0, 0, 0, 1, 2 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/adversarial_pursuit/adversarial_pursuit.py", "Python", 130, 0, 0, 100, 26, 256 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/adversarial_pursuit_v4.py", "Python", 5, 0, 0, 0, 1, 6 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battle/__init__.py", "Python", 1, 0, 0, 0, 1, 2 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battle/battle.py", "Python", 164, 0, 0, 115, 27, 306 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battle_v4.py", "Python", 1, 0, 0, 0, 1, 2 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battlefield/__init__.py", "Python", 1, 0, 0, 0, 1, 2 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battlefield/battlefield.py", "Python", 146, 0, 0, 116, 26, 288 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battlefield_v5.py", "Python", 1, 0, 0, 0, 1, 2 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/combined_arms/__init__.py", "Python", 1, 0, 0, 0, 1, 2 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/combined_arms/combined_arms.py", "Python", 259, 0, 0, 118, 38, 415 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/combined_arms_v6.py", "Python", 1, 0, 0, 0, 1, 2 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/gather/__init__.py", "Python", 1, 0, 0, 0, 1, 2 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/gather/gather.py", "Python", 186, 0, 0, 105, 33, 324 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/gather_v5.py", "Python", 1, 0, 0, 0, 1, 2 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/magent_env.py", "Python", 247, 0, 0, 6, 38, 291 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/tiger_deer/__init__.py", "Python", 1, 0, 0, 0, 1, 2 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/tiger_deer/tiger_deer.py", "Python", 141, 0, 0, 88, 28, 257 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/tiger_deer_v4.py", "Python", 1, 0, 0, 0, 1, 2 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/gridworld.py", "Python", 531, 0, 0, 287, 98, 916 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/magent_env.py", "Python", 58, 0, 0, 0, 12, 70 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/magent_vec_env.py", "Python", 124, 0, 0, 7, 23, 154 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/render.py", "Python", 289, 0, 0, 2, 47, 338 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/utility.py", "Python", 81, 0, 0, 16, 23, 120 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/pettingzoo/__init__.py", "Python", 23, 0, 0, 0, 2, 25 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/pettingzoo/pettingzoo_env.py", "Python", 90, 0, 0, 3, 17, 110 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/pettingzoo/pettingzoo_vec_env.py", "Python", 130, 0, 0, 5, 22, 157 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/starcraft2/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/starcraft2/sc2_env.py", "Python", 54, 0, 0, 0, 11, 65 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/starcraft2/sc2_vec_env.py", "Python", 261, 0, 0, 12, 30, 303 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/vector_envs/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/vector_envs/env_utils.py", "Python", 100, 0, 0, 11, 26, 137 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/vector_envs/subproc_vec_env.py", "Python", 132, 0, 0, 18, 26, 176 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/vector_envs/vector_env.py", "Python", 60, 0, 0, 28, 16, 104 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/__init__.py", "Python", 111, 0, 0, 0, 6, 117 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/agent.py", "Python", 39, 0, 0, 0, 10, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/agents_marl.py", "Python", 88, 0, 0, 0, 18, 106 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/coma_agents.py", "Python", 90, 0, 0, 1, 13, 104 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/dcg_agents.py", "Python", 86, 0, 0, 0, 12, 98 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/iddpg_agents.py", "Python", 80, 0, 0, 0, 11, 91 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/iql_agents.py", "Python", 71, 0, 0, 0, 13, 84 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/isac_agents.py", "Python", 79, 0, 0, 0, 11, 90 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/maddpg_agents.py", "Python", 80, 0, 0, 0, 11, 91 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/mappoclip_agents.py", "Python", 83, 0, 0, 0, 14, 97 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/mappokl_agents.py", "Python", 84, 0, 0, 1, 14, 99 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/masac_agents.py", "Python", 79, 0, 0, 0, 11, 90 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/matd3_agents.py", "Python", 84, 0, 0, 0, 12, 96 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/mfac_agents.py", "Python", 93, 0, 0, 1, 16, 110 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/mfq_agents.py", "Python", 97, 0, 0, 0, 13, 110 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/qmix_agents.py", "Python", 73, 0, 0, 0, 12, 85 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/qtran_agents.py", "Python", 81, 0, 0, 0, 13, 94 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/vdac_agents.py", "Python", 91, 0, 0, 0, 14, 105 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/vdn_agents.py", "Python", 72, 0, 0, 0, 12, 84 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/wqmix_agents.py", "Python", 76, 0, 0, 0, 12, 88 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/a2c_agent.py", "Python", 128, 0, 0, 0, 15, 143 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/ddpg_agent.py", "Python", 122, 0, 0, 0, 14, 136 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/mpdqn_agent.py", "Python", 165, 0, 0, 1, 19, 185 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/pdqn_agent.py", "Python", 153, 0, 0, 1, 18, 172 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/pg_agent.py", "Python", 125, 0, 0, 0, 15, 140 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/ppg_agent.py", "Python", 145, 0, 0, 5, 19, 169 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/ppoclip_agent.py", "Python", 129, 0, 0, 0, 17, 146 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/ppokl_agent.py", "Python", 129, 0, 0, 0, 17, 146 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/sac_agent.py", "Python", 121, 0, 0, 0, 17, 138 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/sacdis_agent.py", "Python", 120, 0, 0, 2, 17, 139 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/spdqn_agent.py", "Python", 172, 0, 0, 1, 20, 193 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/td3_agent.py", "Python", 123, 0, 0, 0, 14, 137 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/C51_agent.py", "Python", 125, 0, 0, 1, 20, 146 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/cdqn_agent.py", "Python", 125, 0, 0, 1, 20, 146 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/cldqn_agent.py", "Python", 125, 0, 0, 1, 20, 146 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/ddqn_agent.py", "Python", 125, 0, 0, 1, 20, 146 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/dqn_agent.py", "Python", 125, 0, 0, 1, 20, 146 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/dueldqn_agent.py", "Python", 126, 0, 0, 1, 20, 147 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/ldqn_agent.py", "Python", 125, 0, 0, 1, 20, 146 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/noisydqn_agent.py", "Python", 124, 0, 0, 1, 21, 146 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/perdqn_agent.py", "Python", 130, 0, 0, 1, 22, 153 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/qrdqn_agent.py", "Python", 125, 0, 0, 1, 20, 146 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/__init__.py", "Python", 49, 0, 0, 0, 4, 53 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/learner.py", "Python", 87, 0, 0, 1, 12, 100 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/coma_learner.py", "Python", 118, 0, 0, 9, 17, 144 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/dcg_learner.py", "Python", 138, 0, 0, 10, 17, 165 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/iddpg_learner.py", "Python", 75, 0, 0, 7, 11, 93 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/iql_learner.py", "Python", 56, 0, 0, 8, 8, 72 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/isac_learner.py", "Python", 84, 0, 0, 7, 13, 104 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/maddpg_learner.py", "Python", 80, 0, 0, 10, 10, 100 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/mappoclip_learner.py", "Python", 77, 0, 0, 8, 12, 97 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/mappokl_learner.py", "Python", 82, 0, 0, 13, 12, 107 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/masac_learner.py", "Python", 84, 0, 0, 7, 12, 103 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/matd3_learner.py", "Python", 104, 0, 0, 7, 13, 124 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/mfac_learner.py", "Python", 103, 0, 0, 10, 14, 127 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/mfq_learner.py", "Python", 65, 0, 0, 7, 10, 82 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/qmix_learner.py", "Python", 61, 0, 0, 8, 9, 78 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/qtran_learner.py", "Python", 98, 0, 0, 7, 14, 119 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/vdac_learner.py", "Python", 50, 0, 0, 6, 10, 66 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/vdn_learner.py", "Python", 60, 0, 0, 9, 8, 77 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/wqmix_learner.py", "Python", 84, 0, 0, 12, 12, 108 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/a2c_learner.py", "Python", 46, 0, 0, 7, 9, 62 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/ddpg_learner.py", "Python", 56, 0, 0, 2, 11, 69 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/mpdqn_learner.py", "Python", 81, 0, 0, 6, 14, 101 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/pdqn_learner.py", "Python", 61, 0, 0, 6, 12, 79 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/pg_learner.py", "Python", 40, 0, 0, 4, 8, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/ppg_learner.py", "Python", 79, 0, 0, 4, 11, 94 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/ppoclip_learner.py", "Python", 51, 0, 0, 8, 7, 66 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/ppokl_learner.py", "Python", 51, 0, 0, 2, 7, 60 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/sac_learner.py", "Python", 55, 0, 0, 1, 12, 68 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/sacdis_learner.py", "Python", 61, 0, 0, 2, 12, 75 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/spdqn_learner.py", "Python", 82, 0, 0, 6, 14, 102 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/td3_learner.py", "Python", 60, 0, 0, 7, 11, 78 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/c51_learner.py", "Python", 59, 0, 0, 4, 15, 78 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/cdqn_learner.py", "Python", 45, 0, 0, 5, 10, 60 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/cldqn_learner.py", "Python", 45, 0, 0, 5, 10, 60 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/ddqn_learner.py", "Python", 48, 0, 0, 2, 11, 61 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/dqn_learner.py", "Python", 45, 0, 0, 5, 10, 60 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/dueldqn_learner.py", "Python", 45, 0, 0, 2, 10, 57 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/ldqn_learner.py", "Python", 45, 0, 0, 5, 10, 60 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/perdqn_learner.py", "Python", 50, 0, 0, 5, 13, 68 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/qrdqn_learner.py", "Python", 54, 0, 0, 5, 11, 70 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/__init__.py", "Python", 150, 0, 0, 3, 8, 161 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/categorical.py", "Python", 201, 0, 0, 60, 42, 303 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/categorical_marl.py", "Python", 252, 0, 0, 1, 39, 292 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/deterministic.py", "Python", 716, 0, 0, 20, 108, 844 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/deterministic_marl.py", "Python", 440, 0, 0, 3, 70, 513 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/gaussian.py", "Python", 207, 0, 0, 12, 35, 254 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/gaussian_marl.py", "Python", 247, 0, 0, 5, 43, 295 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/mixers.py", "Python", 195, 0, 0, 8, 29, 232 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/representations/__init__.py", "Python", 35, 0, 0, 0, 4, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/representations/networks.py", "Python", 266, 0, 0, 5, 44, 315 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/runners/__init__.py", "Python", 7, 0, 0, 0, 2, 9 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/runners/runner_basic.py", "Python", 85, 0, 0, 2, 16, 103 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/runners/runner_drl.py", "Python", 71, 0, 0, 0, 8, 79 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/runners/runner_marl.py", "Python", 105, 0, 0, 3, 18, 126 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/__init__.py", "Python", 2, 0, 0, 0, 0, 2 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/distributions.py", "Python", 46, 0, 0, 0, 18, 64 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/input_reformat.py", "Python", 83, 0, 0, 0, 11, 94 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/layers.py", "Python", 90, 0, 0, 0, 12, 102 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/operations.py", "Python", 47, 0, 0, 0, 12, 59 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/set_trainer.py", "Python", 32, 0, 0, 0, 7, 39 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/__init__.py", "Python", 109, 0, 0, 4, 9, 122 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/agent.py", "Python", 114, 0, 0, 6, 17, 137 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/agents_marl.py", "Python", 83, 0, 0, 2, 17, 102 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/coma_agents.py", "Python", 65, 0, 0, 2, 10, 77 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/dcg_agents.py", "Python", 89, 0, 0, 2, 12, 103 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/iddpg_agents.py", "Python", 82, 0, 0, 0, 11, 93 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/iql_agents.py", "Python", 73, 0, 0, 2, 11, 86 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/isac_agents.py", "Python", 81, 0, 0, 0, 11, 92 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/maddpg_agents.py", "Python", 83, 0, 0, 0, 11, 94 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/mappoclip_agents.py", "Python", 86, 0, 0, 0, 14, 100 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/mappokl_agents.py", "Python", 85, 0, 0, 0, 14, 99 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/masac_agents.py", "Python", 81, 0, 0, 0, 11, 92 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/matd3_agents.py", "Python", 83, 0, 0, 0, 11, 94 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/mfac_agents.py", "Python", 90, 0, 0, 0, 16, 106 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/mfq_agents.py", "Python", 98, 0, 0, 0, 12, 110 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/qmix_agents.py", "Python", 76, 0, 0, 2, 11, 89 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/qtran_agents.py", "Python", 83, 0, 0, 2, 12, 97 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/vdac_agents.py", "Python", 94, 0, 0, 0, 14, 108 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/vdn_agents.py", "Python", 75, 0, 0, 2, 11, 88 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/wqmix_agents.py", "Python", 78, 0, 0, 2, 11, 91 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/a2c_agent.py", "Python", 125, 0, 0, 1, 18, 144 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/ddpg_agent.py", "Python", 111, 0, 0, 1, 18, 130 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/mpdqn_agent.py", "Python", 161, 0, 0, 0, 19, 180 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/pdqn_agent.py", "Python", 159, 0, 0, 0, 19, 178 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/pg_agent.py", "Python", 125, 0, 0, 1, 19, 145 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/ppg_agent.py", "Python", 128, 0, 0, 4, 19, 151 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/ppoclip_agent.py", "Python", 127, 0, 0, 1, 18, 146 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/ppokl_agent.py", "Python", 122, 0, 0, 1, 18, 141 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/sac_agent.py", "Python", 108, 0, 0, 1, 19, 128 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/sacdis_agent.py", "Python", 115, 0, 0, 2, 16, 133 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/spdqn_agent.py", "Python", 165, 0, 0, 0, 19, 184 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/td3_agent.py", "Python", 112, 0, 0, 1, 18, 131 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/c51_agent.py", "Python", 117, 0, 0, 2, 19, 138 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/ddqn_agent.py", "Python", 117, 0, 0, 2, 19, 138 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/dqn_agent.py", "Python", 117, 0, 0, 2, 18, 137 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/drqn_agent.py", "Python", 131, 0, 0, 2, 18, 151 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/dueldqn_agent.py", "Python", 117, 0, 0, 2, 19, 138 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/noisydqn_agent.py", "Python", 116, 0, 0, 2, 19, 137 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/perdqn_agent.py", "Python", 123, 0, 0, 2, 20, 145 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/qrdqn_agent.py", "Python", 117, 0, 0, 2, 19, 138 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/__init__.py", "Python", 47, 0, 0, 0, 4, 51 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/learner.py", "Python", 66, 0, 0, 2, 12, 80 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/coma_learner.py", "Python", 115, 0, 0, 8, 17, 140 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/dcg_learner.py", "Python", 155, 0, 0, 11, 20, 186 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/iddpg_learner.py", "Python", 77, 0, 0, 7, 12, 96 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/iql_learner.py", "Python", 58, 0, 0, 5, 12, 75 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/isac_learner.py", "Python", 82, 0, 0, 5, 13, 100 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/maddpg_learner.py", "Python", 77, 0, 0, 9, 12, 98 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/mappoclip_learner.py", "Python", 77, 0, 0, 7, 12, 96 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/mappokl_learner.py", "Python", 86, 0, 0, 7, 14, 107 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/masac_learner.py", "Python", 82, 0, 0, 5, 13, 100 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/matd3_learner.py", "Python", 83, 0, 0, 6, 11, 100 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/mfac_learner.py", "Python", 91, 0, 0, 11, 14, 116 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/mfq_learner.py", "Python", 73, 0, 0, 8, 13, 94 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/qmix_learner.py", "Python", 61, 0, 0, 7, 11, 79 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/qtran_learner.py", "Python", 92, 0, 0, 8, 12, 112 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/vdac_learner.py", "Python", 64, 0, 0, 6, 12, 82 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/vdn_learner.py", "Python", 59, 0, 0, 6, 12, 77 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/wqmix_learner.py", "Python", 83, 0, 0, 11, 14, 108 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/a2c_learner.py", "Python", 43, 0, 0, 0, 9, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/ddpg_learner.py", "Python", 63, 0, 0, 2, 12, 77 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/mpdqn_learner.py", "Python", 68, 0, 0, 2, 12, 82 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/pdqn_learner.py", "Python", 68, 0, 0, 2, 12, 82 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/pg_learner.py", "Python", 37, 0, 0, 0, 11, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/ppg_learner.py", "Python", 95, 0, 0, 1, 15, 111 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/ppoclip_learner.py", "Python", 47, 0, 0, 1, 8, 56 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/ppokl_learner.py", "Python", 56, 0, 0, 1, 9, 66 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/sac_learner.py", "Python", 65, 0, 0, 3, 12, 80 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/sacdis_learner.py", "Python", 69, 0, 0, 3, 12, 84 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/spdqn_learner.py", "Python", 72, 0, 0, 2, 12, 86 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/td3_learner.py", "Python", 63, 0, 0, 6, 11, 80 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/c51_learner.py", "Python", 41, 0, 0, 0, 13, 54 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/cdqn_learner.py", "Python", 38, 0, 0, 1, 8, 47 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/cldqn_learner.py", "Python", 40, 0, 0, 1, 8, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/ddqn_learner.py", "Python", 40, 0, 0, 1, 9, 50 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/dqn_learner.py", "Python", 41, 0, 0, 0, 8, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/drqn_learner.py", "Python", 44, 0, 0, 2, 11, 57 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/dueldqn_learner.py", "Python", 39, 0, 0, 1, 8, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/ldqn_learner.py", "Python", 39, 0, 0, 1, 8, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/perdqn_learner.py", "Python", 41, 0, 0, 1, 9, 51 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/qrdqn_learner.py", "Python", 39, 0, 0, 1, 7, 47 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/__init__.py", "Python", 166, 0, 0, 3, 9, 178 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/categorical.py", "Python", 195, 0, 0, 3, 31, 229 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/categorical_marl.py", "Python", 253, 0, 0, 1, 30, 284 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/deterministic.py", "Python", 706, 0, 0, 0, 97, 803 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/deterministic_marl.py", "Python", 680, 0, 0, 26, 81, 787 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/gaussian.py", "Python", 215, 0, 0, 2, 32, 249 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/gaussian_marl.py", "Python", 215, 0, 0, 3, 29, 247 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/mixers.py", "Python", 204, 0, 0, 8, 32, 244 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/representations/__init__.py", "Python", 40, 0, 0, 0, 5, 45 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/representations/networks.py", "Python", 288, 0, 0, 1, 46, 335 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/runners/__init__.py", "Python", 7, 0, 0, 0, 2, 9 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/runners/runner_basic.py", "Python", 126, 0, 0, 3, 19, 148 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/runners/runner_drl.py", "Python", 103, 0, 0, 9, 16, 128 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/runners/runner_marl.py", "Python", 105, 0, 0, 3, 18, 126 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/__init__.py", "Python", 3, 0, 0, 0, 0, 3 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/distributions.py", "Python", 70, 0, 0, 0, 28, 98 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/input_reformat.py", "Python", 82, 0, 0, 0, 12, 94 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/layers.py", "Python", 107, 0, 0, 0, 13, 120 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/operations.py", "Python", 51, 0, 0, 3, 17, 71 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/__init__.py", "Python", 104, 0, 0, 0, 6, 110 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/agent.py", "Python", 115, 0, 0, 6, 17, 138 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/agents_marl.py", "Python", 72, 0, 0, 3, 15, 90 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/coma_agents.py", "Python", 77, 0, 0, 4, 11, 92 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/dcg_agents.py", "Python", 99, 0, 0, 0, 11, 110 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/iddpg_agents.py", "Python", 58, 0, 0, 0, 6, 64 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/iql_agents.py", "Python", 81, 0, 0, 0, 11, 92 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/isac_agents.py", "Python", 57, 0, 0, 0, 7, 64 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/maddpg_agents.py", "Python", 57, 0, 0, 0, 7, 64 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/mappo_agents.py", "Python", 102, 0, 0, 4, 11, 117 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/masac_agents.py", "Python", 57, 0, 0, 0, 8, 65 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/matd3_agents.py", "Python", 61, 0, 0, 0, 7, 68 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/mfac_agents.py", "Python", 73, 0, 0, 0, 11, 84 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/mfq_agents.py", "Python", 77, 0, 0, 0, 10, 87 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/qmix_agents.py", "Python", 84, 0, 0, 0, 11, 95 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/qtran_agents.py", "Python", 58, 0, 0, 0, 9, 67 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/vdac_agents.py", "Python", 69, 0, 0, 0, 10, 79 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/vdn_agents.py", "Python", 83, 0, 0, 0, 11, 94 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/wqmix_agents.py", "Python", 86, 0, 0, 0, 11, 97 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/a2c_agent.py", "Python", 144, 0, 0, 1, 17, 162 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/ddpg_agent.py", "Python", 116, 0, 0, 1, 18, 135 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/mpdqn_agent.py", "Python", 159, 0, 0, 0, 19, 178 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/pdqn_agent.py", "Python", 158, 0, 0, 0, 20, 178 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/pg_agent.py", "Python", 134, 0, 0, 1, 15, 150 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/ppg_agent.py", "Python", 149, 0, 0, 4, 18, 171 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/ppoclip_agent.py", "Python", 148, 0, 0, 1, 19, 168 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/ppokl_agent.py", "Python", 146, 0, 0, 1, 18, 165 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/sac_agent.py", "Python", 112, 0, 0, 1, 19, 132 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/sacdis_agent.py", "Python", 119, 0, 0, 1, 16, 136 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/spdqn_agent.py", "Python", 157, 0, 0, 0, 19, 176 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/td3_agent.py", "Python", 116, 0, 0, 1, 18, 135 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/c51_agent.py", "Python", 121, 0, 0, 2, 19, 142 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/ddqn_agent.py", "Python", 122, 0, 0, 2, 18, 142 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/dqn_agent.py", "Python", 121, 0, 0, 2, 18, 141 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/drqn_agent.py", "Python", 138, 0, 0, 2, 20, 160 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/dueldqn_agent.py", "Python", 122, 0, 0, 2, 19, 143 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/noisydqn_agent.py", "Python", 122, 0, 0, 2, 19, 143 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/perdqn_agent.py", "Python", 128, 0, 0, 2, 20, 150 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/qrdqn_agent.py", "Python", 122, 0, 0, 2, 19, 143 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/__init__.py", "Python", 43, 0, 0, 1, 4, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/learner.py", "Python", 79, 0, 0, 0, 17, 96 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/coma_learner.py", "Python", 98, 0, 0, 8, 16, 122 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/dcg_learner.py", "Python", 188, 0, 0, 8, 22, 218 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/iddpg_learner.py", "Python", 64, 0, 0, 5, 11, 80 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/iql_learner.py", "Python", 104, 0, 0, 9, 21, 134 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/isac_learner.py", "Python", 70, 0, 0, 6, 11, 87 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/maddpg_learner.py", "Python", 67, 0, 0, 9, 10, 86 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/mappo_learner.py", "Python", 178, 0, 0, 14, 20, 212 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/masac_learner.py", "Python", 70, 0, 0, 6, 11, 87 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/matd3_learner.py", "Python", 76, 0, 0, 6, 9, 91 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/mfac_learner.py", "Python", 80, 0, 0, 10, 13, 103 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/mfq_learner.py", "Python", 57, 0, 0, 7, 11, 75 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/qmix_learner.py", "Python", 111, 0, 0, 11, 18, 140 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/qtran_learner.py", "Python", 84, 0, 0, 8, 11, 103 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/vdac_learner.py", "Python", 50, 0, 0, 6, 10, 66 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/vdn_learner.py", "Python", 108, 0, 0, 14, 18, 140 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/wqmix_learner.py", "Python", 168, 0, 0, 19, 23, 210 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/a2c_learner.py", "Python", 41, 0, 0, 1, 9, 51 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/ddpg_learner.py", "Python", 44, 0, 0, 3, 10, 57 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/mpdqn_learner.py", "Python", 46, 0, 0, 2, 12, 60 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/pdqn_learner.py", "Python", 46, 0, 0, 2, 19, 67 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/pg_learner.py", "Python", 35, 0, 0, 1, 9, 45 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/ppg_learner.py", "Python", 78, 0, 0, 2, 11, 91 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/ppoclip_learner.py", "Python", 54, 0, 0, 2, 10, 66 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/ppokl_learner.py", "Python", 52, 0, 0, 2, 9, 63 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/sac_learner.py", "Python", 44, 0, 0, 3, 10, 57 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/sacdis_learner.py", "Python", 50, 0, 0, 5, 10, 65 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/spdqn_learner.py", "Python", 46, 0, 0, 2, 12, 60 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/td3_learner.py", "Python", 49, 0, 0, 6, 9, 64 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/c51_learner.py", "Python", 41, 0, 0, 1, 9, 51 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/ddqn_learner.py", "Python", 39, 0, 0, 1, 11, 51 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/dqn_learner.py", "Python", 38, 0, 0, 1, 9, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/drqn_learner.py", "Python", 42, 0, 0, 2, 11, 55 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/dueldqn_learner.py", "Python", 38, 0, 0, 1, 9, 48 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/perdqn_learner.py", "Python", 39, 0, 0, 1, 9, 49 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/qrdqn_learner.py", "Python", 37, 0, 0, 1, 8, 46 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/ssl_rl/__init__.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/ssl_rl/curl_learner.py", "Python", 0, 0, 0, 0, 1, 1 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/__init__.py", "Python", 159, 0, 0, 3, 8, 170 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/categorical.py", "Python", 208, 0, 0, 7, 34, 249 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/categorical_marl.py", "Python", 222, 0, 0, 6, 28, 256 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/coordination_graph.py", "Python", 68, 0, 0, 1, 9, 78 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/deterministic.py", "Python", 743, 0, 0, 2, 97, 842 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/deterministic_marl.py", "Python", 504, 0, 0, 4, 64, 572 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/gaussian.py", "Python", 217, 0, 0, 2, 31, 250 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/gaussian_marl.py", "Python", 188, 0, 0, 4, 31, 223 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/mixers.py", "Python", 117, 0, 0, 6, 19, 142 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/representations/__init__.py", "Python", 38, 0, 0, 0, 6, 44 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/representations/cnn.py", "Python", 83, 0, 0, 1, 10, 94 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/representations/mlp.py", "Python", 42, 0, 0, 2, 8, 52 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/representations/rnn.py", "Python", 71, 0, 0, 0, 8, 79 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/__init__.py", "Python", 13, 0, 0, 0, 2, 15 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_basic.py", "Python", 11, 0, 0, 2, 6, 19 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_drl.py", "Python", 119, 0, 0, 3, 14, 136 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_football.py", "Python", 102, 0, 0, 5, 18, 125 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_magent.py", "Python", 5, 0, 0, 0, 3, 8 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_pettingzoo.py", "Python", 339, 0, 0, 11, 43, 393 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_sc2.py", "Python", 319, 0, 0, 13, 39, 371 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/__init__.py", "Python", 22, 0, 0, 0, 4, 26 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/distributions.py", "Python", 72, 0, 0, 0, 29, 101 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/input_reformat.py", "Python", 104, 0, 0, 0, 15, 119 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/layers.py", "Python", 101, 0, 0, 0, 12, 113 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/operations.py", "Python", 86, 0, 0, 0, 18, 104 -"/home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/value_norm.py", "Python", 54, 0, 0, 3, 20, 77 -"Total", "-", 36964, 13, 6419, 2416, 6986, 52798 \ No newline at end of file diff --git a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/results.json b/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/results.json deleted file mode 100644 index d77dfcfd3..000000000 --- a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/results.json +++ /dev/null @@ -1 +0,0 @@ -{"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/runners/runner_drl.py":{"language":"Python","code":103,"comment":9,"blank":16},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/learner.py":{"language":"Python","code":87,"comment":1,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/runners/runner_marl.py":{"language":"Python","code":105,"comment":3,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/__init__.py":{"language":"Python","code":49,"comment":0,"blank":4},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/football/raw_env.py":{"language":"Python","code":90,"comment":2,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/pettingzoo/__init__.py":{"language":"Python","code":23,"comment":0,"blank":2},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/football/__init__.py":{"language":"Python","code":20,"comment":19,"blank":2},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/__init__.py":{"language":"Python","code":60,"comment":0,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/pettingzoo/pettingzoo_vec_env.py":{"language":"Python","code":130,"comment":5,"blank":22},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/ldqn_learner.py":{"language":"Python","code":45,"comment":5,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/pettingzoo/pettingzoo_env.py":{"language":"Python","code":90,"comment":3,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/football/gfootball_env.py":{"language":"Python","code":64,"comment":0,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/representations/networks.py":{"language":"Python","code":288,"comment":1,"blank":46},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/c51_learner.py":{"language":"Python","code":59,"comment":4,"blank":15},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/football/gfootball_vec_env.py":{"language":"Python","code":81,"comment":0,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/categorical.py":{"language":"Python","code":201,"comment":60,"blank":42},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/gaussian_marl.py":{"language":"Python","code":247,"comment":5,"blank":43},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/gaussian.py":{"language":"Python","code":207,"comment":12,"blank":35},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/categorical_marl.py":{"language":"Python","code":252,"comment":1,"blank":39},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/mixers.py":{"language":"Python","code":195,"comment":8,"blank":29},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/cdqn_learner.py":{"language":"Python","code":45,"comment":5,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/ppokl_learner.py":{"language":"Python","code":51,"comment":2,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/__init__.py":{"language":"Python","code":150,"comment":3,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/qrdqn_learner.py":{"language":"Python","code":54,"comment":5,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/mpdqn_learner.py":{"language":"Python","code":81,"comment":6,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/runners/runner_basic.py":{"language":"Python","code":85,"comment":2,"blank":16},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/pdqn_learner.py":{"language":"Python","code":61,"comment":6,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/deterministic.py":{"language":"Python","code":716,"comment":20,"blank":108},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/cldqn_learner.py":{"language":"Python","code":45,"comment":5,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/runners/__init__.py":{"language":"Python","code":7,"comment":0,"blank":2},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/dqn_learner.py":{"language":"Python","code":45,"comment":5,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/dueldqn_agent.py":{"language":"Python","code":126,"comment":1,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/ppoclip_learner.py":{"language":"Python","code":51,"comment":8,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/perdqn_agent.py":{"language":"Python","code":130,"comment":1,"blank":22},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/qrdqn_agent.py":{"language":"Python","code":125,"comment":1,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/dqn_agent.py":{"language":"Python","code":125,"comment":1,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/deterministic_marl.py":{"language":"Python","code":440,"comment":3,"blank":70},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/ldqn_agent.py":{"language":"Python","code":125,"comment":1,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/ddqn_agent.py":{"language":"Python","code":125,"comment":1,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/runners/runner_drl.py":{"language":"Python","code":71,"comment":0,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/C51_agent.py":{"language":"Python","code":125,"comment":1,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/ppg_learner.py":{"language":"Python","code":79,"comment":4,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/cdqn_agent.py":{"language":"Python","code":125,"comment":1,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/cldqn_agent.py":{"language":"Python","code":125,"comment":1,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/runners/runner_marl.py":{"language":"Python","code":105,"comment":3,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/agent.py":{"language":"Python","code":39,"comment":0,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/a2c_learner.py":{"language":"Python","code":46,"comment":7,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/noisydqn_agent.py":{"language":"Python","code":124,"comment":1,"blank":21},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/agents_marl.py":{"language":"Python","code":88,"comment":0,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/perdqn_learner.py":{"language":"Python","code":50,"comment":5,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/__init__.py":{"language":"Python","code":111,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/dueldqn_learner.py":{"language":"Python","code":45,"comment":2,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/ddqn_learner.py":{"language":"Python","code":48,"comment":2,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/ddpg_learner.py":{"language":"Python","code":56,"comment":2,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/td3_learner.py":{"language":"Python","code":60,"comment":7,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/spdqn_agent.py":{"language":"Python","code":172,"comment":1,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/sac_learner.py":{"language":"Python","code":55,"comment":1,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/pg_learner.py":{"language":"Python","code":40,"comment":4,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/ppokl_agent.py":{"language":"Python","code":129,"comment":0,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/sacdis_learner.py":{"language":"Python","code":61,"comment":2,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/ppoclip_agent.py":{"language":"Python","code":129,"comment":0,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/isac_agents.py":{"language":"Python","code":79,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/wqmix_agents.py":{"language":"Python","code":76,"comment":0,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/ddpg_agent.py":{"language":"Python","code":122,"comment":0,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/sac_agent.py":{"language":"Python","code":121,"comment":0,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/spdqn_learner.py":{"language":"Python","code":82,"comment":6,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/qmix_agents.py":{"language":"Python","code":73,"comment":0,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/pdqn_agent.py":{"language":"Python","code":153,"comment":1,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/pg_agent.py":{"language":"Python","code":125,"comment":0,"blank":15},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/vdac_learner.py":{"language":"Python","code":50,"comment":6,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/vdac_agents.py":{"language":"Python","code":91,"comment":0,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/representations/__init__.py":{"language":"Python","code":35,"comment":0,"blank":4},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/representations/__init__.py":{"language":"Python","code":40,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/starcraft2/sc2_env.py":{"language":"Python","code":54,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/ppg_agent.py":{"language":"Python","code":145,"comment":5,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/mappokl_agents.py":{"language":"Python","code":84,"comment":1,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/layers.py":{"language":"Python","code":90,"comment":0,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/qtran_agents.py":{"language":"Python","code":81,"comment":0,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/mappoclip_agents.py":{"language":"Python","code":83,"comment":0,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/maddpg_agents.py":{"language":"Python","code":80,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/vdn_agents.py":{"language":"Python","code":72,"comment":0,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/iql_learner.py":{"language":"Python","code":56,"comment":8,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/__init__.py":{"language":"Python","code":2,"comment":0,"blank":0},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/vdn_learner.py":{"language":"Python","code":60,"comment":9,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/iql_agents.py":{"language":"Python","code":71,"comment":0,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/iddpg_agents.py":{"language":"Python","code":80,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/__init__.py":{"language":"Python","code":19,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/sacdis_agent.py":{"language":"Python","code":120,"comment":2,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/magent_env.py":{"language":"Python","code":58,"comment":0,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/starcraft2/sc2_vec_env.py":{"language":"Python","code":261,"comment":12,"blank":30},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/mappokl_learner.py":{"language":"Python","code":82,"comment":13,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/matd3_agents.py":{"language":"Python","code":84,"comment":0,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/distributions.py":{"language":"Python","code":46,"comment":0,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/input_reformat.py":{"language":"Python","code":83,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/operations.py":{"language":"Python","code":47,"comment":0,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/set_trainer.py":{"language":"Python","code":32,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/isac_learner.py":{"language":"Python","code":84,"comment":7,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/masac_agents.py":{"language":"Python","code":79,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/render.py":{"language":"Python","code":289,"comment":2,"blank":47},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/magent_vec_env.py":{"language":"Python","code":124,"comment":7,"blank":23},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/representations/networks.py":{"language":"Python","code":266,"comment":5,"blank":44},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/mfac_agents.py":{"language":"Python","code":93,"comment":1,"blank":16},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/mappoclip_learner.py":{"language":"Python","code":77,"comment":8,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/mpdqn_agent.py":{"language":"Python","code":165,"comment":1,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/coma_agents.py":{"language":"Python","code":90,"comment":1,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/mfac_learner.py":{"language":"Python","code":103,"comment":10,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/dcg_learner.py":{"language":"Python","code":138,"comment":10,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/a2c_agent.py":{"language":"Python","code":128,"comment":0,"blank":15},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/magent_env.py":{"language":"Python","code":247,"comment":6,"blank":38},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/dcg_agents.py":{"language":"Python","code":86,"comment":0,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/starcraft2/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/mfq_agents.py":{"language":"Python","code":97,"comment":0,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/masac_learner.py":{"language":"Python","code":84,"comment":7,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/mfq_learner.py":{"language":"Python","code":65,"comment":7,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environment.py":{"language":"Python","code":25,"comment":4,"blank":15},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/qtran_learner.py":{"language":"Python","code":98,"comment":7,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/__init__.py":{"language":"Python","code":3,"comment":0,"blank":3},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/gym/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/vector_envs/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/matd3_learner.py":{"language":"Python","code":104,"comment":7,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/qmix_learner.py":{"language":"Python","code":61,"comment":8,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/iddpg_learner.py":{"language":"Python","code":75,"comment":7,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/vector_envs/vector_env.py":{"language":"Python","code":60,"comment":28,"blank":16},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/gym/gym_env.py":{"language":"Python","code":180,"comment":41,"blank":33},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/vector_envs/subproc_vec_env.py":{"language":"Python","code":132,"comment":18,"blank":26},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/c_lib.py":{"language":"Python","code":26,"comment":5,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/gym/gym_vec_env.py":{"language":"Python","code":196,"comment":17,"blank":28},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/gather_v5.py":{"language":"Python","code":1,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/combined_arms/__init__.py":{"language":"Python","code":1,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/utility.py":{"language":"Python","code":81,"comment":16,"blank":23},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/coma_learner.py":{"language":"Python","code":118,"comment":9,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/combined_arms_v6.py":{"language":"Python","code":1,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battle/battle.py":{"language":"Python","code":164,"comment":115,"blank":27},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/adversarial_pursuit_v4.py":{"language":"Python","code":5,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/tiger_deer/tiger_deer.py":{"language":"Python","code":141,"comment":88,"blank":28},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/tiger_deer/__init__.py":{"language":"Python","code":1,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battlefield_v5.py":{"language":"Python","code":1,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/tiger_deer_v4.py":{"language":"Python","code":1,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battle_v4.py":{"language":"Python","code":1,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/vector_envs/env_utils.py":{"language":"Python","code":100,"comment":11,"blank":26},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battle/__init__.py":{"language":"Python","code":1,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/gather/__init__.py":{"language":"Python","code":1,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/combined_arms/combined_arms.py":{"language":"Python","code":259,"comment":118,"blank":38},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/maddpg_learner.py":{"language":"Python","code":80,"comment":10,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/gather/gather.py":{"language":"Python","code":186,"comment":105,"blank":33},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/wqmix_learner.py":{"language":"Python","code":84,"comment":12,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/runners/__init__.py":{"language":"Python","code":7,"comment":0,"blank":2},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/battle.py":{"language":"Python","code":31,"comment":2,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/runners/runner_basic.py":{"language":"Python","code":126,"comment":3,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battlefield/battlefield.py":{"language":"Python","code":146,"comment":116,"blank":26},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/double_attack.py":{"language":"Python","code":41,"comment":4,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/gridworld.py":{"language":"Python","code":531,"comment":287,"blank":98},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/adversarial_pursuit/adversarial_pursuit.py":{"language":"Python","code":130,"comment":100,"blank":26},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/adversarial_pursuit/__init__.py":{"language":"Python","code":1,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/forest.py":{"language":"Python","code":41,"comment":1,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/__init__.py":{"language":"Python","code":109,"comment":4,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/agents_marl.py":{"language":"Python","code":83,"comment":2,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/pursuit.py":{"language":"Python","code":34,"comment":0,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battlefield/__init__.py":{"language":"Python","code":1,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/__init__.py":{"language":"Python","code":47,"comment":0,"blank":4},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/agent.py":{"language":"Python","code":114,"comment":6,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/ddpg_agent.py":{"language":"Python","code":111,"comment":1,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/operations.py":{"language":"Python","code":51,"comment":3,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/__init__.py":{"language":"Python","code":166,"comment":3,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/mixers.py":{"language":"Python","code":204,"comment":8,"blank":32},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/ppoclip_agent.py":{"language":"Python","code":127,"comment":1,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/input_reformat.py":{"language":"Python","code":82,"comment":0,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/ppokl_agent.py":{"language":"Python","code":122,"comment":1,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/mappoclip_agents.py":{"language":"Python","code":86,"comment":0,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/distributions.py":{"language":"Python","code":70,"comment":0,"blank":28},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/categorical_marl.py":{"language":"Python","code":253,"comment":1,"blank":30},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/sac_agent.py":{"language":"Python","code":108,"comment":1,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/spdqn_agent.py":{"language":"Python","code":165,"comment":0,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/wqmix_agents.py":{"language":"Python","code":78,"comment":2,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/ppg_agent.py":{"language":"Python","code":128,"comment":4,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/deterministic_marl.py":{"language":"Python","code":680,"comment":26,"blank":81},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/gaussian_marl.py":{"language":"Python","code":215,"comment":3,"blank":29},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/pg_agent.py":{"language":"Python","code":125,"comment":1,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/gaussian.py":{"language":"Python","code":215,"comment":2,"blank":32},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/qmix_agents.py":{"language":"Python","code":76,"comment":2,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/pdqn_agent.py":{"language":"Python","code":159,"comment":0,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/isac_agents.py":{"language":"Python","code":81,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/__init__.py":{"language":"Python","code":3,"comment":0,"blank":0},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/a2c_agent.py":{"language":"Python","code":125,"comment":1,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/learner.py":{"language":"Python","code":66,"comment":2,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/categorical.py":{"language":"Python","code":195,"comment":3,"blank":31},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/vdac_agents.py":{"language":"Python","code":94,"comment":0,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/deterministic.py":{"language":"Python","code":706,"comment":0,"blank":97},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/mpdqn_agent.py":{"language":"Python","code":161,"comment":0,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/layers.py":{"language":"Python","code":107,"comment":0,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/qrdqn_learner.py":{"language":"Python","code":39,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/td3_agent.py":{"language":"Python","code":123,"comment":0,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/dcg_learner.py":{"language":"Python","code":155,"comment":11,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/build.sh":{"language":"Shell Script","code":13,"comment":3,"blank":3},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/ldqn_learner.py":{"language":"Python","code":39,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/c51_learner.py":{"language":"Python","code":41,"comment":0,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/coma_agents.py":{"language":"Python","code":65,"comment":2,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/mfq_agents.py":{"language":"Python","code":98,"comment":0,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/mappokl_agents.py":{"language":"Python","code":85,"comment":0,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/qrdqn_agent.py":{"language":"Python","code":117,"comment":2,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/sacdis_agent.py":{"language":"Python","code":115,"comment":2,"blank":16},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/wqmix_learner.py":{"language":"Python","code":83,"comment":11,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/dueldqn_agent.py":{"language":"Python","code":117,"comment":2,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/masac_agents.py":{"language":"Python","code":81,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/masac_learner.py":{"language":"Python","code":82,"comment":5,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/statistic_tools.py":{"language":"Python","code":115,"comment":0,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/maddpg_learner.py":{"language":"Python","code":77,"comment":9,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/memory_tools.py":{"language":"Python","code":397,"comment":91,"blank":70},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/mfac_agents.py":{"language":"Python","code":90,"comment":0,"blank":16},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/cldqn_learner.py":{"language":"Python","code":40,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/perdqn_agent.py":{"language":"Python","code":123,"comment":2,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/matd3_agents.py":{"language":"Python","code":83,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/dcg_agents.py":{"language":"Python","code":89,"comment":2,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/matd3_learner.py":{"language":"Python","code":83,"comment":6,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/dqn_learner.py":{"language":"Python","code":41,"comment":0,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/drqn_agent.py":{"language":"Python","code":131,"comment":2,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/mfac_learner.py":{"language":"Python","code":91,"comment":11,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/value_norm.py":{"language":"Python","code":54,"comment":3,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/dqn_agent.py":{"language":"Python","code":117,"comment":2,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/layers.py":{"language":"Python","code":101,"comment":0,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/__init__.py":{"language":"Python","code":22,"comment":0,"blank":4},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/iddpg_learner.py":{"language":"Python","code":77,"comment":7,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/coma_learner.py":{"language":"Python","code":115,"comment":8,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/__init__.py":{"language":"Python","code":43,"comment":1,"blank":4},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_football.py":{"language":"Python","code":102,"comment":5,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/input_reformat.py":{"language":"Python","code":104,"comment":0,"blank":15},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/representations/cnn.py":{"language":"Python","code":83,"comment":1,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/operations.py":{"language":"Python","code":86,"comment":0,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_sc2.py":{"language":"Python","code":319,"comment":13,"blank":39},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/representations/__init__.py":{"language":"Python","code":38,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/representations/mlp.py":{"language":"Python","code":42,"comment":2,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_magent.py":{"language":"Python","code":5,"comment":0,"blank":3},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/representations/rnn.py":{"language":"Python","code":71,"comment":0,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/mfq_learner.py":{"language":"Python","code":73,"comment":8,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_pettingzoo.py":{"language":"Python","code":339,"comment":11,"blank":43},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/vdac_learner.py":{"language":"Python","code":50,"comment":6,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/c51_learner.py":{"language":"Python","code":41,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_drl.py":{"language":"Python","code":119,"comment":3,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/iql_learner.py":{"language":"Python","code":104,"comment":9,"blank":21},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/ppokl_learner.py":{"language":"Python","code":52,"comment":2,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_basic.py":{"language":"Python","code":11,"comment":2,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/__init__.py":{"language":"Python","code":13,"comment":0,"blank":2},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/vdn_learner.py":{"language":"Python","code":108,"comment":14,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/sac_learner.py":{"language":"Python","code":44,"comment":3,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/qrdqn_learner.py":{"language":"Python","code":37,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/dcg_learner.py":{"language":"Python","code":188,"comment":8,"blank":22},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/a2c_learner.py":{"language":"Python","code":41,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/qtran_learner.py":{"language":"Python","code":84,"comment":8,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/matd3_learner.py":{"language":"Python","code":76,"comment":6,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/mappo_learner.py":{"language":"Python","code":178,"comment":14,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/dueldqn_learner.py":{"language":"Python","code":38,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/td3_learner.py":{"language":"Python","code":49,"comment":6,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/qmix_learner.py":{"language":"Python","code":111,"comment":11,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/wqmix_learner.py":{"language":"Python","code":168,"comment":19,"blank":23},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/maddpg_learner.py":{"language":"Python","code":67,"comment":9,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/ddpg_learner.py":{"language":"Python","code":44,"comment":3,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/iddpg_learner.py":{"language":"Python","code":64,"comment":5,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/dqn_learner.py":{"language":"Python","code":38,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/masac_learner.py":{"language":"Python","code":70,"comment":6,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/pg_learner.py":{"language":"Python","code":35,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/coma_learner.py":{"language":"Python","code":98,"comment":8,"blank":16},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/perdqn_learner.py":{"language":"Python","code":39,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/ppg_learner.py":{"language":"Python","code":78,"comment":2,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/ppoclip_learner.py":{"language":"Python","code":54,"comment":2,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/drqn_learner.py":{"language":"Python","code":42,"comment":2,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/mfq_learner.py":{"language":"Python","code":57,"comment":7,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/sacdis_learner.py":{"language":"Python","code":50,"comment":5,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/ddqn_learner.py":{"language":"Python","code":39,"comment":1,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/pdqn_learner.py":{"language":"Python","code":46,"comment":2,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/mfac_learner.py":{"language":"Python","code":80,"comment":10,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/mpdqn_learner.py":{"language":"Python","code":46,"comment":2,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/isac_learner.py":{"language":"Python","code":70,"comment":6,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/spdqn_learner.py":{"language":"Python","code":46,"comment":2,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/learner.py":{"language":"Python","code":79,"comment":0,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/distributions.py":{"language":"Python","code":72,"comment":0,"blank":29},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/qmix_learner.py":{"language":"Python","code":61,"comment":7,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/ssl_rl/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/ssl_rl/curl_learner.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/mixers.py":{"language":"Python","code":117,"comment":6,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/gaussian_marl.py":{"language":"Python","code":188,"comment":4,"blank":31},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/categorical_marl.py":{"language":"Python","code":222,"comment":6,"blank":28},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/qmix_agents.py":{"language":"Python","code":84,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/vdac_agents.py":{"language":"Python","code":69,"comment":0,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/deterministic.py":{"language":"Python","code":743,"comment":2,"blank":97},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/isac_agents.py":{"language":"Python","code":57,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/gaussian.py":{"language":"Python","code":217,"comment":2,"blank":31},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/vdac_learner.py":{"language":"Python","code":64,"comment":6,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/wqmix_agents.py":{"language":"Python","code":86,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/coordination_graph.py":{"language":"Python","code":68,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/agent.py":{"language":"Python","code":115,"comment":6,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/mfq_agents.py":{"language":"Python","code":77,"comment":0,"blank":10},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/deterministic_marl.py":{"language":"Python","code":504,"comment":4,"blank":64},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/noisydqn_agent.py":{"language":"Python","code":122,"comment":2,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/__init__.py":{"language":"Python","code":159,"comment":3,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/mappo_agents.py":{"language":"Python","code":102,"comment":4,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/categorical.py":{"language":"Python","code":208,"comment":7,"blank":34},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/dcg_agents.py":{"language":"Python","code":99,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/maddpg_agents.py":{"language":"Python","code":57,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/c51_agent.py":{"language":"Python","code":121,"comment":2,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/td3_agent.py":{"language":"Python","code":112,"comment":1,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/coma_agents.py":{"language":"Python","code":77,"comment":4,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/qtran_agents.py":{"language":"Python","code":58,"comment":0,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/dqn_agent.py":{"language":"Python","code":121,"comment":2,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/ddqn_agent.py":{"language":"Python","code":122,"comment":2,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/matd3_agents.py":{"language":"Python","code":61,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/drqn_agent.py":{"language":"Python","code":138,"comment":2,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/vdn_agents.py":{"language":"Python","code":83,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/perdqn_agent.py":{"language":"Python","code":128,"comment":2,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/iql_agents.py":{"language":"Python","code":81,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/qrdqn_agent.py":{"language":"Python","code":122,"comment":2,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/mfac_agents.py":{"language":"Python","code":73,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/iddpg_agents.py":{"language":"Python","code":58,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/agents_marl.py":{"language":"Python","code":72,"comment":3,"blank":15},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/dueldqn_agent.py":{"language":"Python","code":122,"comment":2,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/masac_agents.py":{"language":"Python","code":57,"comment":0,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/__init__.py":{"language":"Python","code":104,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/qtran_learner.py":{"language":"Python","code":92,"comment":8,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/iql_agents.py":{"language":"Python","code":73,"comment":2,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/isac_learner.py":{"language":"Python","code":82,"comment":5,"blank":13},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/segtree_tool.py":{"language":"Python","code":69,"comment":3,"blank":15},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/dueldqn_learner.py":{"language":"Python","code":39,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/c51_agent.py":{"language":"Python","code":117,"comment":2,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/mappoclip_learner.py":{"language":"Python","code":77,"comment":7,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/perdqn_learner.py":{"language":"Python","code":41,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/vdn_agents.py":{"language":"Python","code":75,"comment":2,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/common_tools.py":{"language":"Python","code":151,"comment":18,"blank":29},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/iql_learner.py":{"language":"Python","code":58,"comment":5,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/noisydqn_agent.py":{"language":"Python","code":116,"comment":2,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/vdn_learner.py":{"language":"Python","code":59,"comment":6,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/drqn_learner.py":{"language":"Python","code":44,"comment":2,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/ddqn_agent.py":{"language":"Python","code":117,"comment":2,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/iddpg_agents.py":{"language":"Python","code":82,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/ddqn_learner.py":{"language":"Python","code":40,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/memory_tools_marl.py":{"language":"Python","code":377,"comment":106,"blank":61},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/qtran_agents.py":{"language":"Python","code":83,"comment":2,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/__init__.py":{"language":"Python","code":5,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/maddpg_agents.py":{"language":"Python","code":83,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/cdqn_learner.py":{"language":"Python","code":38,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/mappokl_learner.py":{"language":"Python","code":86,"comment":7,"blank":14},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/__init__.py":{"language":"Python","code":4,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/atari.yaml":{"language":"YAML","code":40,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/atari.yaml":{"language":"YAML","code":39,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/box2d/BipedalWalker-v3.yaml":{"language":"YAML","code":31,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/box2d/LunarLander-v2.yaml":{"language":"YAML","code":31,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/classic_control/Pendulum-v1.yaml":{"language":"YAML","code":31,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/td3/mujoco.yaml":{"language":"YAML","code":31,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":32,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/classic_control/CartPole-v1.yaml":{"language":"YAML","code":32,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":31,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/mujoco.yaml":{"language":"YAML","code":31,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/classic_control/MountainCar-v0.yaml":{"language":"YAML","code":31,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/classic_control/MountainCar-v1.yaml":{"language":"YAML","code":32,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/classic_control/CartPole-v1.yaml":{"language":"YAML","code":31,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/td3/classic_control/Pendulum-v1.yaml":{"language":"YAML","code":31,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/box2d/CarRacing-v2.yaml":{"language":"YAML","code":34,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/box2d/LunarLander-v2.yaml":{"language":"YAML","code":32,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/5m_vs_6m.yaml":{"language":"YAML","code":55,"comment":2,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/8m_vs_9m.yaml":{"language":"YAML","code":55,"comment":2,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/mpe/simple_spread_v3.yaml":{"language":"YAML","code":45,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/td3/box2d/BipedalWalker-v3.yaml":{"language":"YAML","code":31,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/corridor.yaml":{"language":"YAML","code":55,"comment":2,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/MMM2.yaml":{"language":"YAML","code":55,"comment":2,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/2m_vs_1z.yaml":{"language":"YAML","code":56,"comment":2,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/25m.yaml":{"language":"YAML","code":55,"comment":2,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdac/mpe/simple_spread_v3.yaml":{"language":"YAML","code":41,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/8m.yaml":{"language":"YAML","code":55,"comment":2,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/3m.yaml":{"language":"YAML","code":55,"comment":2,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ippo/sc2/2m_vs_1z.yaml":{"language":"YAML","code":55,"comment":2,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/maddpg/mpe/simple_push_v3.yaml":{"language":"YAML","code":27,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/maddpg/mpe/simple_adversary_v3.yaml":{"language":"YAML","code":35,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/maddpg/mpe/simple_spread_v3.yaml":{"language":"YAML","code":35,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ippo/mpe/simple_spread_v3.yaml":{"language":"YAML","code":44,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ippo/sc2/3m.yaml":{"language":"YAML","code":55,"comment":2,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/isac/mpe/simple_spread_v3.yaml":{"language":"YAML","code":26,"comment":0,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/isac/mpe/simple_push_v3.yaml":{"language":"YAML","code":26,"comment":0,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/matd3/mpe/simple_push_v3.yaml":{"language":"YAML","code":25,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/matd3/mpe/simple_spread_v3.yaml":{"language":"YAML","code":25,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/classic_control/CartPole-v1.yaml":{"language":"YAML","code":31,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/isac/mpe/simple_adversary_v3.yaml":{"language":"YAML","code":26,"comment":0,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qtran/mpe/simple_spread_v3.yaml":{"language":"YAML","code":28,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/classic_control/MountainCar-v0.yaml":{"language":"YAML","code":31,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":31,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/box2d/CarRacing-v2.yaml":{"language":"YAML","code":33,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/basic.yaml":{"language":"YAML","code":13,"comment":3,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mfac/mpe/simple_spread_v3.yaml":{"language":"YAML","code":32,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/mpe/simple_spread_v3.yaml":{"language":"YAML","code":38,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/5m_vs_6m.yaml":{"language":"YAML","code":44,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/box2d/LunarLander-v2.yaml":{"language":"YAML","code":31,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/25m.yaml":{"language":"YAML","code":44,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/8m.yaml":{"language":"YAML","code":44,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/2m_vs_1z.yaml":{"language":"YAML","code":44,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/atari.yaml":{"language":"YAML","code":38,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/MMM2.yaml":{"language":"YAML","code":44,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/box2d/CarRacing-v2.yaml":{"language":"YAML","code":32,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/box2d/LunarLander-v2.yaml":{"language":"YAML","code":30,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/3m.yaml":{"language":"YAML","code":44,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/corridor.yaml":{"language":"YAML","code":44,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/classic_control/MountainCar-v0.yaml":{"language":"YAML","code":30,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/8m_vs_9m.yaml":{"language":"YAML","code":44,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/masac/mpe/simple_push_v3.yaml":{"language":"YAML","code":26,"comment":0,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":30,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/masac/mpe/simple_spread_v3.yaml":{"language":"YAML","code":26,"comment":0,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/classic_control/MountainCar-v0.yaml":{"language":"YAML","code":30,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddpg/mujoco.yaml":{"language":"YAML","code":31,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/atari.yaml":{"language":"YAML","code":38,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/classic_control/CartPole-v1.yaml":{"language":"YAML","code":30,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/atari.yaml":{"language":"YAML","code":38,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/classic_control/CartPole-v1.yaml":{"language":"YAML","code":30,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddpg/classic_control/Pendulum-v1.yaml":{"language":"YAML","code":31,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":30,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/box2d/CarRacing-v2.yaml":{"language":"YAML","code":32,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":30,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/classic_control/CartPole-v1.yaml":{"language":"YAML","code":30,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/box2d/LunarLander-v2.yaml":{"language":"YAML","code":30,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/box2d/LunarLander-v2.yaml":{"language":"YAML","code":30,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddpg/box2d/BipedalWalker-v3.yaml":{"language":"YAML","code":31,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/classic_control/MountainCar-v0.yaml":{"language":"YAML","code":29,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/box2d/CarRacing-v2.yaml":{"language":"YAML","code":32,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/MMM2.yaml":{"language":"YAML","code":41,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/25m.yaml":{"language":"YAML","code":41,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/3m.yaml":{"language":"YAML","code":41,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/classic_control/MountainCar-v0.yaml":{"language":"YAML","code":35,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/corridor.yaml":{"language":"YAML","code":41,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/mujoco.yaml":{"language":"YAML","code":35,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/atari.yaml":{"language":"YAML","code":43,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/8m.yaml":{"language":"YAML","code":41,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/football/3v1.yaml":{"language":"YAML","code":49,"comment":2,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/8m_vs_9m.yaml":{"language":"YAML","code":41,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/classic_control/CartPole-v1.yaml":{"language":"YAML","code":35,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":35,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/5m_vs_6m.yaml":{"language":"YAML","code":41,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/2m_vs_1z.yaml":{"language":"YAML","code":41,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/classic_control/Pendulum-v1.yaml":{"language":"YAML","code":35,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/mpe/simple_spread_v3.yaml":{"language":"YAML","code":35,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/mpe/simple_spread_v3.yaml":{"language":"YAML","code":35,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/coma/mpe/simple_spread_v3.yaml":{"language":"YAML","code":38,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/football/3v1.yaml":{"language":"YAML","code":49,"comment":2,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/box2d/CarRacing-v2.yaml":{"language":"YAML","code":37,"comment":1,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/box2d/BipedalWalker-v3.yaml":{"language":"YAML","code":35,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mpdqn/Platform.yaml":{"language":"YAML","code":25,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/box2d/LunarLander-v2.yaml":{"language":"YAML","code":35,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/8m.yaml":{"language":"YAML","code":40,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/25m.yaml":{"language":"YAML","code":40,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/MMM2.yaml":{"language":"YAML","code":40,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/mpe/simple_spread_v3.yaml":{"language":"YAML","code":44,"comment":0,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/random/mpe/simple_spread.yaml":{"language":"YAML","code":7,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/corridor.yaml":{"language":"YAML","code":40,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/random/mpe/simple_push.yaml":{"language":"YAML","code":7,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/3m.yaml":{"language":"YAML","code":40,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/8m_vs_9m.yaml":{"language":"YAML","code":40,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/5m_vs_6m.yaml":{"language":"YAML","code":40,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/td3_agent.py":{"language":"Python","code":116,"comment":1,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/3m.yaml":{"language":"YAML","code":49,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/corridor.yaml":{"language":"YAML","code":49,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/2m_vs_1z.yaml":{"language":"YAML","code":41,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/mpe/simple_spread_v3.yaml":{"language":"YAML","code":37,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/2m_vs_1z.yaml":{"language":"YAML","code":49,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/8m.yaml":{"language":"YAML","code":49,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/sacdis_agent.py":{"language":"Python","code":119,"comment":1,"blank":16},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/25m.yaml":{"language":"YAML","code":49,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/8m_vs_9m.yaml":{"language":"YAML","code":49,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/5m_vs_6m.yaml":{"language":"YAML","code":49,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/MMM2.yaml":{"language":"YAML","code":49,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/atari.yaml":{"language":"YAML","code":42,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/MMM2.yaml":{"language":"YAML","code":43,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/box2d/CarRacing-v2.yaml":{"language":"YAML","code":36,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/corridor.yaml":{"language":"YAML","code":43,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/box2d/LunarLander-v2.yaml":{"language":"YAML","code":34,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/3m.yaml":{"language":"YAML","code":43,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":34,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/8m.yaml":{"language":"YAML","code":43,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/2m_vs_1z.yaml":{"language":"YAML","code":43,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/25m.yaml":{"language":"YAML","code":43,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/mpdqn_agent.py":{"language":"Python","code":159,"comment":0,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/classic_control/CartPole-v1.yaml":{"language":"YAML","code":34,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/8m_vs_9m.yaml":{"language":"YAML","code":43,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/5m_vs_6m.yaml":{"language":"YAML","code":43,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/classic_control/MountainCar-v0.yaml":{"language":"YAML","code":33,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/random/mpe/simple_adversary.yaml":{"language":"YAML","code":7,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/a2c_agent.py":{"language":"Python","code":144,"comment":1,"blank":17},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/spdqn/Platform-v0.yaml":{"language":"YAML","code":25,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/ppg_agent.py":{"language":"Python","code":149,"comment":4,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pdqn/Platform.yaml":{"language":"YAML","code":25,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/atari.yaml":{"language":"YAML","code":41,"comment":1,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/atari.yaml":{"language":"YAML","code":41,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/mujoco.yaml":{"language":"YAML","code":33,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":33,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/classic_control/CartPole-v1.yaml":{"language":"YAML","code":33,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/classic_control/MountainCar-v0.yaml":{"language":"YAML","code":33,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/classic_control/Pendulum-v1.yaml":{"language":"YAML","code":33,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/box2d/LunarLander-v2.yaml":{"language":"YAML","code":33,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":33,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/classic_control/CartPole-v1.yaml":{"language":"YAML","code":33,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/box2d/CarRacing-v2.yaml":{"language":"YAML","code":35,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/pg_agent.py":{"language":"Python","code":134,"comment":1,"blank":15},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/pdqn_agent.py":{"language":"Python","code":158,"comment":0,"blank":20},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/classic_control/MountainCar-v0.yaml":{"language":"YAML","code":33,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/sac_agent.py":{"language":"Python","code":112,"comment":1,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/ppoclip_agent.py":{"language":"Python","code":148,"comment":1,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/ddpg_agent.py":{"language":"Python","code":116,"comment":1,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/box2d/LunarLander-v2.yaml":{"language":"YAML","code":32,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/box2d/BipedalWalker-v3.yaml":{"language":"YAML","code":32,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iddpg/mpe/simple_spread_v3.yaml":{"language":"YAML","code":25,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/mujoco.yaml":{"language":"YAML","code":33,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/atari.yaml":{"language":"YAML","code":41,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iddpg/mpe/simple_adversary_v3.yaml":{"language":"YAML","code":27,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/classic_control/Pendulum-v1.yaml":{"language":"YAML","code":31,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/classic_control/CartPole-v1.yaml":{"language":"YAML","code":32,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mfq/magent2/adversarial_pursuit_v4.yaml":{"language":"YAML","code":43,"comment":1,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/ppokl_agent.py":{"language":"Python","code":146,"comment":1,"blank":18},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/spdqn_agent.py":{"language":"Python","code":157,"comment":0,"blank":19},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":32,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iddpg/mpe/simple_push_v3.yaml":{"language":"YAML","code":25,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/classic_control/MountainCar-v0.yaml":{"language":"YAML","code":32,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mfq/mpe/simple_spread_v3.yaml":{"language":"YAML","code":25,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/atari.yaml":{"language":"YAML","code":38,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/box2d/BipedalWalker-v3.yaml":{"language":"YAML","code":31,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/box2d/LunarLander-v2.yaml":{"language":"YAML","code":32,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/box2d/CarRacing-v2.yaml":{"language":"YAML","code":32,"comment":1,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/box2d/LunarLander-v2.yaml":{"language":"YAML","code":30,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/mujoco.yaml":{"language":"YAML","code":35,"comment":0,"blank":7},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":35,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/box2d/LunarLander-v2.yaml":{"language":"YAML","code":35,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/classic_control/Pendulum-v1.yaml":{"language":"YAML","code":35,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/classic_control/MountainCar-v0.yaml":{"language":"YAML","code":35,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/classic_control/CartPole-v1.yaml":{"language":"YAML","code":30,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/sacdis_learner.py":{"language":"Python","code":69,"comment":3,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/classic_control/Acrobot-v1.yaml":{"language":"YAML","code":30,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/spdqn_learner.py":{"language":"Python","code":72,"comment":2,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/pg_learner.py":{"language":"Python","code":37,"comment":0,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/td3_learner.py":{"language":"Python","code":63,"comment":6,"blank":11},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/sac_learner.py":{"language":"Python","code":65,"comment":3,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/a2c_learner.py":{"language":"Python","code":43,"comment":0,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/ddpg_learner.py":{"language":"Python","code":63,"comment":2,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/ppg_learner.py":{"language":"Python","code":95,"comment":1,"blank":15},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/ppoclip_learner.py":{"language":"Python","code":47,"comment":1,"blank":8},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/pdqn_learner.py":{"language":"Python","code":68,"comment":2,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/classic_control/MountainCar-v0.yaml":{"language":"YAML","code":30,"comment":0,"blank":6},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/__init__.py":{"language":"Python","code":0,"comment":0,"blank":1},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/ppokl_learner.py":{"language":"Python","code":56,"comment":1,"blank":9},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/mpdqn_learner.py":{"language":"Python","code":68,"comment":2,"blank":12},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/classic_control/CartPole-v1.yaml":{"language":"YAML","code":35,"comment":0,"blank":5},"file:///home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/box2d/BipedalWalker-v3.yaml":{"language":"YAML","code":35,"comment":0,"blank":6}} \ No newline at end of file diff --git a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/results.md b/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/results.md deleted file mode 100644 index 4cd7cb1c6..000000000 --- a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/results.md +++ /dev/null @@ -1,205 +0,0 @@ -# Summary - -Date : 2023-08-23 15:10:05 - -Directory /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy - -Total : 566 files, 43396 codes, 2416 comments, 6986 blanks, all 52798 lines - -Summary / [Details](details.md) / [Diff Summary](diff.md) / [Diff Details](diff-details.md) - -## Languages -| language | files | code | comment | blank | total | -| :--- | ---: | ---: | ---: | ---: | ---: | -| Python | 387 | 36,964 | 2,322 | 5,789 | 45,075 | -| YAML | 178 | 6,419 | 91 | 1,194 | 7,704 | -| Shell Script | 1 | 13 | 3 | 3 | 19 | - -## Directories -| path | files | code | comment | blank | total | -| :--- | ---: | ---: | ---: | ---: | ---: | -| . | 566 | 43,396 | 2,416 | 6,986 | 52,798 | -| . (Files) | 1 | 4 | 0 | 1 | 5 | -| common | 6 | 1,114 | 218 | 189 | 1,521 | -| configs | 179 | 6,419 | 91 | 1,195 | 7,705 | -| configs (Files) | 2 | 13 | 3 | 7 | 23 | -| configs/a2c | 8 | 270 | 1 | 48 | 319 | -| configs/a2c (Files) | 2 | 74 | 1 | 12 | 87 | -| configs/a2c/box2d | 2 | 64 | 0 | 12 | 76 | -| configs/a2c/classic_control | 4 | 132 | 0 | 24 | 156 | -| configs/c51 | 6 | 208 | 2 | 38 | 248 | -| configs/c51 (Files) | 1 | 41 | 1 | 7 | 49 | -| configs/c51/box2d | 2 | 68 | 1 | 13 | 82 | -| configs/c51/classic_control | 3 | 99 | 0 | 18 | 117 | -| configs/coma | 1 | 38 | 0 | 7 | 45 | -| configs/coma/mpe | 1 | 38 | 0 | 7 | 45 | -| configs/dcg | 9 | 436 | 8 | 72 | 516 | -| configs/dcg/mpe | 1 | 44 | 0 | 8 | 52 | -| configs/dcg/sc2 | 8 | 392 | 8 | 64 | 464 | -| configs/ddpg | 3 | 93 | 0 | 16 | 109 | -| configs/ddpg (Files) | 1 | 31 | 0 | 6 | 37 | -| configs/ddpg/box2d | 1 | 31 | 0 | 5 | 36 | -| configs/ddpg/classic_control | 1 | 31 | 0 | 5 | 36 | -| configs/ddqn | 6 | 190 | 2 | 41 | 233 | -| configs/ddqn (Files) | 1 | 38 | 1 | 7 | 46 | -| configs/ddqn/box2d | 2 | 62 | 1 | 13 | 76 | -| configs/ddqn/classic_control | 3 | 90 | 0 | 21 | 111 | -| configs/dqn | 6 | 189 | 2 | 38 | 229 | -| configs/dqn (Files) | 1 | 38 | 1 | 7 | 46 | -| configs/dqn/box2d | 2 | 62 | 1 | 13 | 76 | -| configs/dqn/classic_control | 3 | 89 | 0 | 18 | 107 | -| configs/drqn | 6 | 213 | 2 | 38 | 253 | -| configs/drqn (Files) | 1 | 42 | 1 | 7 | 50 | -| configs/drqn/box2d | 2 | 70 | 1 | 13 | 84 | -| configs/drqn/classic_control | 3 | 101 | 0 | 18 | 119 | -| configs/dueldqn | 6 | 190 | 2 | 38 | 230 | -| configs/dueldqn (Files) | 1 | 38 | 1 | 7 | 46 | -| configs/dueldqn/box2d | 2 | 62 | 1 | 13 | 76 | -| configs/dueldqn/classic_control | 3 | 90 | 0 | 18 | 108 | -| configs/iddpg | 3 | 77 | 0 | 21 | 98 | -| configs/iddpg/mpe | 3 | 77 | 0 | 21 | 98 | -| configs/ippo | 3 | 154 | 5 | 23 | 182 | -| configs/ippo/mpe | 1 | 44 | 1 | 7 | 52 | -| configs/ippo/sc2 | 2 | 110 | 4 | 16 | 130 | -| configs/iql | 10 | 405 | 10 | 69 | 484 | -| configs/iql/football | 1 | 49 | 2 | 7 | 58 | -| configs/iql/mpe | 1 | 35 | 0 | 6 | 41 | -| configs/iql/sc2 | 8 | 321 | 8 | 56 | 385 | -| configs/isac | 3 | 78 | 0 | 24 | 102 | -| configs/isac/mpe | 3 | 78 | 0 | 24 | 102 | -| configs/maddpg | 3 | 97 | 0 | 18 | 115 | -| configs/maddpg/mpe | 3 | 97 | 0 | 18 | 115 | -| configs/mappo | 9 | 486 | 17 | 71 | 574 | -| configs/mappo/mpe | 1 | 45 | 1 | 7 | 53 | -| configs/mappo/sc2 | 8 | 441 | 16 | 64 | 521 | -| configs/masac | 2 | 52 | 0 | 16 | 68 | -| configs/masac/mpe | 2 | 52 | 0 | 16 | 68 | -| configs/matd3 | 2 | 50 | 0 | 14 | 64 | -| configs/matd3/mpe | 2 | 50 | 0 | 14 | 64 | -| configs/mfac | 1 | 32 | 1 | 7 | 40 | -| configs/mfac/mpe | 1 | 32 | 1 | 7 | 40 | -| configs/mfq | 2 | 68 | 1 | 12 | 81 | -| configs/mfq/magent2 | 1 | 43 | 1 | 6 | 50 | -| configs/mfq/mpe | 1 | 25 | 0 | 6 | 31 | -| configs/mpdqn | 1 | 25 | 0 | 7 | 32 | -| configs/noisydqn | 6 | 190 | 2 | 38 | 230 | -| configs/noisydqn (Files) | 1 | 38 | 1 | 7 | 46 | -| configs/noisydqn/box2d | 2 | 62 | 1 | 13 | 76 | -| configs/noisydqn/classic_control | 3 | 90 | 0 | 18 | 108 | -| configs/pdqn | 1 | 25 | 0 | 7 | 32 | -| configs/perdqn | 6 | 202 | 2 | 44 | 248 | -| configs/perdqn (Files) | 1 | 40 | 1 | 8 | 49 | -| configs/perdqn/box2d | 2 | 66 | 1 | 15 | 82 | -| configs/perdqn/classic_control | 3 | 96 | 0 | 21 | 117 | -| configs/pg | 7 | 217 | 0 | 36 | 253 | -| configs/pg (Files) | 1 | 31 | 0 | 5 | 36 | -| configs/pg/box2d | 2 | 62 | 0 | 10 | 72 | -| configs/pg/classic_control | 4 | 124 | 0 | 21 | 145 | -| configs/ppg | 7 | 245 | 0 | 41 | 286 | -| configs/ppg (Files) | 1 | 35 | 0 | 7 | 42 | -| configs/ppg/box2d | 2 | 70 | 0 | 11 | 81 | -| configs/ppg/classic_control | 4 | 140 | 0 | 23 | 163 | -| configs/ppo | 9 | 325 | 2 | 60 | 387 | -| configs/ppo (Files) | 2 | 78 | 1 | 14 | 93 | -| configs/ppo/box2d | 3 | 107 | 1 | 18 | 126 | -| configs/ppo/classic_control | 4 | 140 | 0 | 28 | 168 | -| configs/qmix | 9 | 381 | 8 | 71 | 460 | -| configs/qmix/mpe | 1 | 37 | 0 | 7 | 44 | -| configs/qmix/sc2 | 8 | 344 | 8 | 64 | 416 | -| configs/qrdqn | 6 | 196 | 2 | 38 | 236 | -| configs/qrdqn (Files) | 1 | 39 | 1 | 7 | 47 | -| configs/qrdqn/box2d | 2 | 64 | 1 | 13 | 78 | -| configs/qrdqn/classic_control | 3 | 93 | 0 | 18 | 111 | -| configs/qtran | 1 | 28 | 0 | 6 | 34 | -| configs/qtran/mpe | 1 | 28 | 0 | 6 | 34 | -| configs/random | 3 | 21 | 0 | 3 | 24 | -| configs/random/mpe | 3 | 21 | 0 | 3 | 24 | -| configs/sac | 8 | 264 | 0 | 48 | 312 | -| configs/sac (Files) | 2 | 74 | 0 | 12 | 86 | -| configs/sac/box2d | 2 | 63 | 0 | 12 | 75 | -| configs/sac/classic_control | 4 | 127 | 0 | 24 | 151 | -| configs/spdqn | 1 | 25 | 0 | 7 | 32 | -| configs/td3 | 3 | 93 | 0 | 16 | 109 | -| configs/td3 (Files) | 1 | 31 | 0 | 6 | 37 | -| configs/td3/box2d | 1 | 31 | 0 | 5 | 36 | -| configs/td3/classic_control | 1 | 31 | 0 | 5 | 36 | -| configs/vdac | 1 | 41 | 1 | 8 | 50 | -| configs/vdac/mpe | 1 | 41 | 1 | 8 | 50 | -| configs/vdn | 10 | 412 | 10 | 69 | 491 | -| configs/vdn/football | 1 | 49 | 2 | 7 | 58 | -| configs/vdn/mpe | 1 | 35 | 0 | 6 | 41 | -| configs/vdn/sc2 | 8 | 328 | 8 | 56 | 392 | -| configs/wqmix | 9 | 390 | 8 | 78 | 476 | -| configs/wqmix/mpe | 1 | 38 | 0 | 6 | 44 | -| configs/wqmix/sc2 | 8 | 352 | 8 | 72 | 432 | -| environment | 53 | 4,146 | 1,136 | 769 | 6,051 | -| environment (Files) | 1 | 60 | 0 | 8 | 68 | -| environment/football | 4 | 255 | 21 | 32 | 308 | -| environment/gym | 3 | 376 | 58 | 62 | 496 | -| environment/magent2 | 35 | 2,605 | 980 | 515 | 4,100 | -| environment/magent2 (Files) | 9 | 1,166 | 325 | 241 | 1,732 | -| environment/magent2/builtin | 6 | 147 | 7 | 43 | 197 | -| environment/magent2/builtin (Files) | 1 | 0 | 0 | 1 | 1 | -| environment/magent2/builtin/config | 5 | 147 | 7 | 42 | 196 | -| environment/magent2/environments | 20 | 1,292 | 648 | 231 | 2,171 | -| environment/magent2/environments (Files) | 8 | 260 | 6 | 47 | 313 | -| environment/magent2/environments/adversarial_pursuit | 2 | 131 | 100 | 27 | 258 | -| environment/magent2/environments/battle | 2 | 165 | 115 | 28 | 308 | -| environment/magent2/environments/battlefield | 2 | 147 | 116 | 27 | 290 | -| environment/magent2/environments/combined_arms | 2 | 260 | 118 | 39 | 417 | -| environment/magent2/environments/gather | 2 | 187 | 105 | 34 | 326 | -| environment/magent2/environments/tiger_deer | 2 | 142 | 88 | 29 | 259 | -| environment/pettingzoo | 3 | 243 | 8 | 41 | 292 | -| environment/starcraft2 | 3 | 315 | 12 | 42 | 369 | -| environment/vector_envs | 4 | 292 | 57 | 69 | 418 | -| mindspore | 109 | 10,515 | 384 | 1,632 | 12,531 | -| mindspore (Files) | 1 | 0 | 0 | 1 | 1 | -| mindspore/agents | 45 | 4,524 | 23 | 656 | 5,203 | -| mindspore/agents (Files) | 3 | 238 | 0 | 34 | 272 | -| mindspore/agents/multi_agent_rl | 18 | 1,399 | 3 | 215 | 1,617 | -| mindspore/agents/policy_gradient | 13 | 1,632 | 10 | 203 | 1,845 | -| mindspore/agents/qlearning_family | 11 | 1,255 | 10 | 204 | 1,469 | -| mindspore/learners | 43 | 2,714 | 239 | 449 | 3,402 | -| mindspore/learners (Files) | 2 | 136 | 1 | 16 | 153 | -| mindspore/learners/multi_agent_rl | 18 | 1,419 | 145 | 203 | 1,767 | -| mindspore/learners/policy_gradient | 13 | 723 | 55 | 129 | 907 | -| mindspore/learners/qlearning_family | 10 | 436 | 38 | 101 | 575 | -| mindspore/policies | 8 | 2,408 | 112 | 374 | 2,894 | -| mindspore/representations | 2 | 301 | 5 | 48 | 354 | -| mindspore/runners | 4 | 268 | 5 | 44 | 317 | -| mindspore/utils | 6 | 300 | 0 | 60 | 360 | -| tensorflow | 107 | 10,513 | 281 | 1,605 | 12,399 | -| tensorflow (Files) | 1 | 0 | 0 | 1 | 1 | -| tensorflow/agents | 43 | 4,221 | 55 | 620 | 4,896 | -| tensorflow/agents (Files) | 3 | 306 | 12 | 43 | 361 | -| tensorflow/agents/multi_agent_rl | 18 | 1,402 | 14 | 204 | 1,620 | -| tensorflow/agents/policy_gradient | 13 | 1,558 | 13 | 221 | 1,792 | -| tensorflow/agents/qlearning_family | 9 | 955 | 16 | 152 | 1,123 | -| tensorflow/learners | 44 | 2,676 | 161 | 467 | 3,304 | -| tensorflow/learners (Files) | 2 | 113 | 2 | 16 | 131 | -| tensorflow/learners/multi_agent_rl | 18 | 1,415 | 127 | 225 | 1,767 | -| tensorflow/learners/policy_gradient | 13 | 746 | 23 | 136 | 905 | -| tensorflow/learners/qlearning_family | 11 | 402 | 9 | 90 | 501 | -| tensorflow/policies | 8 | 2,634 | 46 | 341 | 3,021 | -| tensorflow/representations | 2 | 328 | 1 | 51 | 380 | -| tensorflow/runners | 4 | 341 | 15 | 55 | 411 | -| tensorflow/utils | 5 | 313 | 3 | 70 | 386 | -| torch | 111 | 10,685 | 306 | 1,595 | 12,586 | -| torch (Files) | 1 | 0 | 0 | 1 | 1 | -| torch/agents | 42 | 4,124 | 45 | 561 | 4,730 | -| torch/agents (Files) | 3 | 291 | 9 | 38 | 338 | -| torch/agents/multi_agent_rl | 17 | 1,179 | 8 | 153 | 1,340 | -| torch/agents/policy_gradient | 13 | 1,658 | 12 | 217 | 1,887 | -| torch/agents/qlearning_family | 9 | 996 | 16 | 153 | 1,165 | -| torch/learners | 42 | 2,554 | 186 | 457 | 3,197 | -| torch/learners (Files) | 2 | 122 | 1 | 21 | 144 | -| torch/learners/multi_agent_rl | 17 | 1,573 | 146 | 236 | 1,955 | -| torch/learners/policy_gradient | 13 | 585 | 31 | 131 | 747 | -| torch/learners/qlearning_family | 8 | 274 | 8 | 67 | 349 | -| torch/learners/ssl_rl | 2 | 0 | 0 | 2 | 2 | -| torch/policies | 9 | 2,426 | 35 | 321 | 2,782 | -| torch/representations | 4 | 234 | 3 | 32 | 269 | -| torch/runners | 7 | 908 | 34 | 125 | 1,067 | -| torch/utils | 6 | 439 | 3 | 98 | 540 | - -Summary / [Details](details.md) / [Diff Summary](diff.md) / [Diff Details](diff-details.md) \ No newline at end of file diff --git a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/results.txt b/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/results.txt deleted file mode 100644 index 8df00c32f..000000000 --- a/xuanpolicy/.VSCodeCounter/2023-08-23_15-10-05/results.txt +++ /dev/null @@ -1,774 +0,0 @@ -Date : 2023-08-23 15:10:05 -Directory : /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy -Total : 566 files, 43396 codes, 2416 comments, 6986 blanks, all 52798 lines - -Languages -+--------------+------------+------------+------------+------------+------------+ -| language | files | code | comment | blank | total | -+--------------+------------+------------+------------+------------+------------+ -| Python | 387 | 36,964 | 2,322 | 5,789 | 45,075 | -| YAML | 178 | 6,419 | 91 | 1,194 | 7,704 | -| Shell Script | 1 | 13 | 3 | 3 | 19 | -+--------------+------------+------------+------------+------------+------------+ - -Directories -+----------------------------------------------------------------------------------------------------------------------------------------------+------------+------------+------------+------------+------------+ -| path | files | code | comment | blank | total | -+----------------------------------------------------------------------------------------------------------------------------------------------+------------+------------+------------+------------+------------+ -| . | 566 | 43,396 | 2,416 | 6,986 | 52,798 | -| . (Files) | 1 | 4 | 0 | 1 | 5 | -| common | 6 | 1,114 | 218 | 189 | 1,521 | -| configs | 179 | 6,419 | 91 | 1,195 | 7,705 | -| configs (Files) | 2 | 13 | 3 | 7 | 23 | -| configs/a2c | 8 | 270 | 1 | 48 | 319 | -| configs/a2c (Files) | 2 | 74 | 1 | 12 | 87 | -| configs/a2c/box2d | 2 | 64 | 0 | 12 | 76 | -| configs/a2c/classic_control | 4 | 132 | 0 | 24 | 156 | -| configs/c51 | 6 | 208 | 2 | 38 | 248 | -| configs/c51 (Files) | 1 | 41 | 1 | 7 | 49 | -| configs/c51/box2d | 2 | 68 | 1 | 13 | 82 | -| configs/c51/classic_control | 3 | 99 | 0 | 18 | 117 | -| configs/coma | 1 | 38 | 0 | 7 | 45 | -| configs/coma/mpe | 1 | 38 | 0 | 7 | 45 | -| configs/dcg | 9 | 436 | 8 | 72 | 516 | -| configs/dcg/mpe | 1 | 44 | 0 | 8 | 52 | -| configs/dcg/sc2 | 8 | 392 | 8 | 64 | 464 | -| configs/ddpg | 3 | 93 | 0 | 16 | 109 | -| configs/ddpg (Files) | 1 | 31 | 0 | 6 | 37 | -| configs/ddpg/box2d | 1 | 31 | 0 | 5 | 36 | -| configs/ddpg/classic_control | 1 | 31 | 0 | 5 | 36 | -| configs/ddqn | 6 | 190 | 2 | 41 | 233 | -| configs/ddqn (Files) | 1 | 38 | 1 | 7 | 46 | -| configs/ddqn/box2d | 2 | 62 | 1 | 13 | 76 | -| configs/ddqn/classic_control | 3 | 90 | 0 | 21 | 111 | -| configs/dqn | 6 | 189 | 2 | 38 | 229 | -| configs/dqn (Files) | 1 | 38 | 1 | 7 | 46 | -| configs/dqn/box2d | 2 | 62 | 1 | 13 | 76 | -| configs/dqn/classic_control | 3 | 89 | 0 | 18 | 107 | -| configs/drqn | 6 | 213 | 2 | 38 | 253 | -| configs/drqn (Files) | 1 | 42 | 1 | 7 | 50 | -| configs/drqn/box2d | 2 | 70 | 1 | 13 | 84 | -| configs/drqn/classic_control | 3 | 101 | 0 | 18 | 119 | -| configs/dueldqn | 6 | 190 | 2 | 38 | 230 | -| configs/dueldqn (Files) | 1 | 38 | 1 | 7 | 46 | -| configs/dueldqn/box2d | 2 | 62 | 1 | 13 | 76 | -| configs/dueldqn/classic_control | 3 | 90 | 0 | 18 | 108 | -| configs/iddpg | 3 | 77 | 0 | 21 | 98 | -| configs/iddpg/mpe | 3 | 77 | 0 | 21 | 98 | -| configs/ippo | 3 | 154 | 5 | 23 | 182 | -| configs/ippo/mpe | 1 | 44 | 1 | 7 | 52 | -| configs/ippo/sc2 | 2 | 110 | 4 | 16 | 130 | -| configs/iql | 10 | 405 | 10 | 69 | 484 | -| configs/iql/football | 1 | 49 | 2 | 7 | 58 | -| configs/iql/mpe | 1 | 35 | 0 | 6 | 41 | -| configs/iql/sc2 | 8 | 321 | 8 | 56 | 385 | -| configs/isac | 3 | 78 | 0 | 24 | 102 | -| configs/isac/mpe | 3 | 78 | 0 | 24 | 102 | -| configs/maddpg | 3 | 97 | 0 | 18 | 115 | -| configs/maddpg/mpe | 3 | 97 | 0 | 18 | 115 | -| configs/mappo | 9 | 486 | 17 | 71 | 574 | -| configs/mappo/mpe | 1 | 45 | 1 | 7 | 53 | -| configs/mappo/sc2 | 8 | 441 | 16 | 64 | 521 | -| configs/masac | 2 | 52 | 0 | 16 | 68 | -| configs/masac/mpe | 2 | 52 | 0 | 16 | 68 | -| configs/matd3 | 2 | 50 | 0 | 14 | 64 | -| configs/matd3/mpe | 2 | 50 | 0 | 14 | 64 | -| configs/mfac | 1 | 32 | 1 | 7 | 40 | -| configs/mfac/mpe | 1 | 32 | 1 | 7 | 40 | -| configs/mfq | 2 | 68 | 1 | 12 | 81 | -| configs/mfq/magent2 | 1 | 43 | 1 | 6 | 50 | -| configs/mfq/mpe | 1 | 25 | 0 | 6 | 31 | -| configs/mpdqn | 1 | 25 | 0 | 7 | 32 | -| configs/noisydqn | 6 | 190 | 2 | 38 | 230 | -| configs/noisydqn (Files) | 1 | 38 | 1 | 7 | 46 | -| configs/noisydqn/box2d | 2 | 62 | 1 | 13 | 76 | -| configs/noisydqn/classic_control | 3 | 90 | 0 | 18 | 108 | -| configs/pdqn | 1 | 25 | 0 | 7 | 32 | -| configs/perdqn | 6 | 202 | 2 | 44 | 248 | -| configs/perdqn (Files) | 1 | 40 | 1 | 8 | 49 | -| configs/perdqn/box2d | 2 | 66 | 1 | 15 | 82 | -| configs/perdqn/classic_control | 3 | 96 | 0 | 21 | 117 | -| configs/pg | 7 | 217 | 0 | 36 | 253 | -| configs/pg (Files) | 1 | 31 | 0 | 5 | 36 | -| configs/pg/box2d | 2 | 62 | 0 | 10 | 72 | -| configs/pg/classic_control | 4 | 124 | 0 | 21 | 145 | -| configs/ppg | 7 | 245 | 0 | 41 | 286 | -| configs/ppg (Files) | 1 | 35 | 0 | 7 | 42 | -| configs/ppg/box2d | 2 | 70 | 0 | 11 | 81 | -| configs/ppg/classic_control | 4 | 140 | 0 | 23 | 163 | -| configs/ppo | 9 | 325 | 2 | 60 | 387 | -| configs/ppo (Files) | 2 | 78 | 1 | 14 | 93 | -| configs/ppo/box2d | 3 | 107 | 1 | 18 | 126 | -| configs/ppo/classic_control | 4 | 140 | 0 | 28 | 168 | -| configs/qmix | 9 | 381 | 8 | 71 | 460 | -| configs/qmix/mpe | 1 | 37 | 0 | 7 | 44 | -| configs/qmix/sc2 | 8 | 344 | 8 | 64 | 416 | -| configs/qrdqn | 6 | 196 | 2 | 38 | 236 | -| configs/qrdqn (Files) | 1 | 39 | 1 | 7 | 47 | -| configs/qrdqn/box2d | 2 | 64 | 1 | 13 | 78 | -| configs/qrdqn/classic_control | 3 | 93 | 0 | 18 | 111 | -| configs/qtran | 1 | 28 | 0 | 6 | 34 | -| configs/qtran/mpe | 1 | 28 | 0 | 6 | 34 | -| configs/random | 3 | 21 | 0 | 3 | 24 | -| configs/random/mpe | 3 | 21 | 0 | 3 | 24 | -| configs/sac | 8 | 264 | 0 | 48 | 312 | -| configs/sac (Files) | 2 | 74 | 0 | 12 | 86 | -| configs/sac/box2d | 2 | 63 | 0 | 12 | 75 | -| configs/sac/classic_control | 4 | 127 | 0 | 24 | 151 | -| configs/spdqn | 1 | 25 | 0 | 7 | 32 | -| configs/td3 | 3 | 93 | 0 | 16 | 109 | -| configs/td3 (Files) | 1 | 31 | 0 | 6 | 37 | -| configs/td3/box2d | 1 | 31 | 0 | 5 | 36 | -| configs/td3/classic_control | 1 | 31 | 0 | 5 | 36 | -| configs/vdac | 1 | 41 | 1 | 8 | 50 | -| configs/vdac/mpe | 1 | 41 | 1 | 8 | 50 | -| configs/vdn | 10 | 412 | 10 | 69 | 491 | -| configs/vdn/football | 1 | 49 | 2 | 7 | 58 | -| configs/vdn/mpe | 1 | 35 | 0 | 6 | 41 | -| configs/vdn/sc2 | 8 | 328 | 8 | 56 | 392 | -| configs/wqmix | 9 | 390 | 8 | 78 | 476 | -| configs/wqmix/mpe | 1 | 38 | 0 | 6 | 44 | -| configs/wqmix/sc2 | 8 | 352 | 8 | 72 | 432 | -| environment | 53 | 4,146 | 1,136 | 769 | 6,051 | -| environment (Files) | 1 | 60 | 0 | 8 | 68 | -| environment/football | 4 | 255 | 21 | 32 | 308 | -| environment/gym | 3 | 376 | 58 | 62 | 496 | -| environment/magent2 | 35 | 2,605 | 980 | 515 | 4,100 | -| environment/magent2 (Files) | 9 | 1,166 | 325 | 241 | 1,732 | -| environment/magent2/builtin | 6 | 147 | 7 | 43 | 197 | -| environment/magent2/builtin (Files) | 1 | 0 | 0 | 1 | 1 | -| environment/magent2/builtin/config | 5 | 147 | 7 | 42 | 196 | -| environment/magent2/environments | 20 | 1,292 | 648 | 231 | 2,171 | -| environment/magent2/environments (Files) | 8 | 260 | 6 | 47 | 313 | -| environment/magent2/environments/adversarial_pursuit | 2 | 131 | 100 | 27 | 258 | -| environment/magent2/environments/battle | 2 | 165 | 115 | 28 | 308 | -| environment/magent2/environments/battlefield | 2 | 147 | 116 | 27 | 290 | -| environment/magent2/environments/combined_arms | 2 | 260 | 118 | 39 | 417 | -| environment/magent2/environments/gather | 2 | 187 | 105 | 34 | 326 | -| environment/magent2/environments/tiger_deer | 2 | 142 | 88 | 29 | 259 | -| environment/pettingzoo | 3 | 243 | 8 | 41 | 292 | -| environment/starcraft2 | 3 | 315 | 12 | 42 | 369 | -| environment/vector_envs | 4 | 292 | 57 | 69 | 418 | -| mindspore | 109 | 10,515 | 384 | 1,632 | 12,531 | -| mindspore (Files) | 1 | 0 | 0 | 1 | 1 | -| mindspore/agents | 45 | 4,524 | 23 | 656 | 5,203 | -| mindspore/agents (Files) | 3 | 238 | 0 | 34 | 272 | -| mindspore/agents/multi_agent_rl | 18 | 1,399 | 3 | 215 | 1,617 | -| mindspore/agents/policy_gradient | 13 | 1,632 | 10 | 203 | 1,845 | -| mindspore/agents/qlearning_family | 11 | 1,255 | 10 | 204 | 1,469 | -| mindspore/learners | 43 | 2,714 | 239 | 449 | 3,402 | -| mindspore/learners (Files) | 2 | 136 | 1 | 16 | 153 | -| mindspore/learners/multi_agent_rl | 18 | 1,419 | 145 | 203 | 1,767 | -| mindspore/learners/policy_gradient | 13 | 723 | 55 | 129 | 907 | -| mindspore/learners/qlearning_family | 10 | 436 | 38 | 101 | 575 | -| mindspore/policies | 8 | 2,408 | 112 | 374 | 2,894 | -| mindspore/representations | 2 | 301 | 5 | 48 | 354 | -| mindspore/runners | 4 | 268 | 5 | 44 | 317 | -| mindspore/utils | 6 | 300 | 0 | 60 | 360 | -| tensorflow | 107 | 10,513 | 281 | 1,605 | 12,399 | -| tensorflow (Files) | 1 | 0 | 0 | 1 | 1 | -| tensorflow/agents | 43 | 4,221 | 55 | 620 | 4,896 | -| tensorflow/agents (Files) | 3 | 306 | 12 | 43 | 361 | -| tensorflow/agents/multi_agent_rl | 18 | 1,402 | 14 | 204 | 1,620 | -| tensorflow/agents/policy_gradient | 13 | 1,558 | 13 | 221 | 1,792 | -| tensorflow/agents/qlearning_family | 9 | 955 | 16 | 152 | 1,123 | -| tensorflow/learners | 44 | 2,676 | 161 | 467 | 3,304 | -| tensorflow/learners (Files) | 2 | 113 | 2 | 16 | 131 | -| tensorflow/learners/multi_agent_rl | 18 | 1,415 | 127 | 225 | 1,767 | -| tensorflow/learners/policy_gradient | 13 | 746 | 23 | 136 | 905 | -| tensorflow/learners/qlearning_family | 11 | 402 | 9 | 90 | 501 | -| tensorflow/policies | 8 | 2,634 | 46 | 341 | 3,021 | -| tensorflow/representations | 2 | 328 | 1 | 51 | 380 | -| tensorflow/runners | 4 | 341 | 15 | 55 | 411 | -| tensorflow/utils | 5 | 313 | 3 | 70 | 386 | -| torch | 111 | 10,685 | 306 | 1,595 | 12,586 | -| torch (Files) | 1 | 0 | 0 | 1 | 1 | -| torch/agents | 42 | 4,124 | 45 | 561 | 4,730 | -| torch/agents (Files) | 3 | 291 | 9 | 38 | 338 | -| torch/agents/multi_agent_rl | 17 | 1,179 | 8 | 153 | 1,340 | -| torch/agents/policy_gradient | 13 | 1,658 | 12 | 217 | 1,887 | -| torch/agents/qlearning_family | 9 | 996 | 16 | 153 | 1,165 | -| torch/learners | 42 | 2,554 | 186 | 457 | 3,197 | -| torch/learners (Files) | 2 | 122 | 1 | 21 | 144 | -| torch/learners/multi_agent_rl | 17 | 1,573 | 146 | 236 | 1,955 | -| torch/learners/policy_gradient | 13 | 585 | 31 | 131 | 747 | -| torch/learners/qlearning_family | 8 | 274 | 8 | 67 | 349 | -| torch/learners/ssl_rl | 2 | 0 | 0 | 2 | 2 | -| torch/policies | 9 | 2,426 | 35 | 321 | 2,782 | -| torch/representations | 4 | 234 | 3 | 32 | 269 | -| torch/runners | 7 | 908 | 34 | 125 | 1,067 | -| torch/utils | 6 | 439 | 3 | 98 | 540 | -+----------------------------------------------------------------------------------------------------------------------------------------------+------------+------------+------------+------------+------------+ - -Files -+----------------------------------------------------------------------------------------------------------------------------------------------+--------------+------------+------------+------------+------------+ -| filename | language | code | comment | blank | total | -+----------------------------------------------------------------------------------------------------------------------------------------------+--------------+------------+------------+------------+------------+ -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/__init__.py | Python | 4 | 0 | 1 | 5 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/__init__.py | Python | 5 | 0 | 1 | 6 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/common_tools.py | Python | 151 | 18 | 29 | 198 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/memory_tools.py | Python | 397 | 91 | 70 | 558 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/memory_tools_marl.py | Python | 377 | 106 | 61 | 544 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/segtree_tool.py | Python | 69 | 3 | 15 | 87 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/common/statistic_tools.py | Python | 115 | 0 | 13 | 128 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/atari.yaml | YAML | 41 | 1 | 6 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/box2d/BipedalWalker-v3.yaml | YAML | 32 | 0 | 6 | 38 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/box2d/LunarLander-v2.yaml | YAML | 32 | 0 | 6 | 38 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/classic_control/Acrobot-v1.yaml | YAML | 33 | 0 | 6 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/classic_control/CartPole-v1.yaml | YAML | 33 | 0 | 6 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/classic_control/MountainCar-v0.yaml | YAML | 33 | 0 | 6 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/classic_control/Pendulum-v1.yaml | YAML | 33 | 0 | 6 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/a2c/mujoco.yaml | YAML | 33 | 0 | 6 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/basic.yaml | YAML | 13 | 3 | 6 | 22 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/atari.yaml | YAML | 41 | 1 | 7 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/box2d/CarRacing-v2.yaml | YAML | 35 | 1 | 7 | 43 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/box2d/LunarLander-v2.yaml | YAML | 33 | 0 | 6 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/classic_control/Acrobot-v1.yaml | YAML | 33 | 0 | 6 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/classic_control/CartPole-v1.yaml | YAML | 33 | 0 | 6 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/c51/classic_control/MountainCar-v0.yaml | YAML | 33 | 0 | 6 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/coma/mpe/simple_spread_v3.yaml | YAML | 38 | 0 | 7 | 45 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/mpe/simple_spread_v3.yaml | YAML | 44 | 0 | 8 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/25m.yaml | YAML | 49 | 1 | 8 | 58 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/2m_vs_1z.yaml | YAML | 49 | 1 | 8 | 58 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/3m.yaml | YAML | 49 | 1 | 8 | 58 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/5m_vs_6m.yaml | YAML | 49 | 1 | 8 | 58 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/8m.yaml | YAML | 49 | 1 | 8 | 58 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/8m_vs_9m.yaml | YAML | 49 | 1 | 8 | 58 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/MMM2.yaml | YAML | 49 | 1 | 8 | 58 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dcg/sc2/corridor.yaml | YAML | 49 | 1 | 8 | 58 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddpg/box2d/BipedalWalker-v3.yaml | YAML | 31 | 0 | 5 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddpg/classic_control/Pendulum-v1.yaml | YAML | 31 | 0 | 5 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddpg/mujoco.yaml | YAML | 31 | 0 | 6 | 37 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/atari.yaml | YAML | 38 | 1 | 7 | 46 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/box2d/CarRacing-v2.yaml | YAML | 32 | 1 | 7 | 40 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/box2d/LunarLander-v2.yaml | YAML | 30 | 0 | 6 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/classic_control/Acrobot-v1.yaml | YAML | 30 | 0 | 7 | 37 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/classic_control/CartPole-v1.yaml | YAML | 30 | 0 | 7 | 37 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ddqn/classic_control/MountainCar-v0.yaml | YAML | 30 | 0 | 7 | 37 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/atari.yaml | YAML | 38 | 1 | 7 | 46 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/box2d/CarRacing-v2.yaml | YAML | 32 | 1 | 7 | 40 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/box2d/LunarLander-v2.yaml | YAML | 30 | 0 | 6 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/classic_control/Acrobot-v1.yaml | YAML | 30 | 0 | 6 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/classic_control/CartPole-v1.yaml | YAML | 30 | 0 | 6 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dqn/classic_control/MountainCar-v0.yaml | YAML | 29 | 0 | 6 | 35 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/atari.yaml | YAML | 42 | 1 | 7 | 50 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/box2d/CarRacing-v2.yaml | YAML | 36 | 1 | 7 | 44 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/box2d/LunarLander-v2.yaml | YAML | 34 | 0 | 6 | 40 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/classic_control/Acrobot-v1.yaml | YAML | 34 | 0 | 6 | 40 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/classic_control/CartPole-v1.yaml | YAML | 34 | 0 | 6 | 40 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/drqn/classic_control/MountainCar-v0.yaml | YAML | 33 | 0 | 6 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/atari.yaml | YAML | 38 | 1 | 7 | 46 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/box2d/CarRacing-v2.yaml | YAML | 32 | 1 | 7 | 40 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/box2d/LunarLander-v2.yaml | YAML | 30 | 0 | 6 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/classic_control/Acrobot-v1.yaml | YAML | 30 | 0 | 6 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/classic_control/CartPole-v1.yaml | YAML | 30 | 0 | 6 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/dueldqn/classic_control/MountainCar-v0.yaml | YAML | 30 | 0 | 6 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iddpg/mpe/simple_adversary_v3.yaml | YAML | 27 | 0 | 7 | 34 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iddpg/mpe/simple_push_v3.yaml | YAML | 25 | 0 | 7 | 32 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iddpg/mpe/simple_spread_v3.yaml | YAML | 25 | 0 | 7 | 32 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ippo/mpe/simple_spread_v3.yaml | YAML | 44 | 1 | 7 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ippo/sc2/2m_vs_1z.yaml | YAML | 55 | 2 | 8 | 65 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ippo/sc2/3m.yaml | YAML | 55 | 2 | 8 | 65 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/football/3v1.yaml | YAML | 49 | 2 | 7 | 58 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/mpe/simple_spread_v3.yaml | YAML | 35 | 0 | 6 | 41 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/25m.yaml | YAML | 40 | 1 | 7 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/2m_vs_1z.yaml | YAML | 41 | 1 | 7 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/3m.yaml | YAML | 40 | 1 | 7 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/5m_vs_6m.yaml | YAML | 40 | 1 | 7 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/8m.yaml | YAML | 40 | 1 | 7 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/8m_vs_9m.yaml | YAML | 40 | 1 | 7 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/MMM2.yaml | YAML | 40 | 1 | 7 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/iql/sc2/corridor.yaml | YAML | 40 | 1 | 7 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/isac/mpe/simple_adversary_v3.yaml | YAML | 26 | 0 | 8 | 34 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/isac/mpe/simple_push_v3.yaml | YAML | 26 | 0 | 8 | 34 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/isac/mpe/simple_spread_v3.yaml | YAML | 26 | 0 | 8 | 34 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/maddpg/mpe/simple_adversary_v3.yaml | YAML | 35 | 0 | 5 | 40 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/maddpg/mpe/simple_push_v3.yaml | YAML | 27 | 0 | 7 | 34 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/maddpg/mpe/simple_spread_v3.yaml | YAML | 35 | 0 | 6 | 41 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/mpe/simple_spread_v3.yaml | YAML | 45 | 1 | 7 | 53 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/25m.yaml | YAML | 55 | 2 | 8 | 65 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/2m_vs_1z.yaml | YAML | 56 | 2 | 8 | 66 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/3m.yaml | YAML | 55 | 2 | 8 | 65 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/5m_vs_6m.yaml | YAML | 55 | 2 | 8 | 65 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/8m.yaml | YAML | 55 | 2 | 8 | 65 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/8m_vs_9m.yaml | YAML | 55 | 2 | 8 | 65 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/MMM2.yaml | YAML | 55 | 2 | 8 | 65 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mappo/sc2/corridor.yaml | YAML | 55 | 2 | 8 | 65 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/masac/mpe/simple_push_v3.yaml | YAML | 26 | 0 | 8 | 34 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/masac/mpe/simple_spread_v3.yaml | YAML | 26 | 0 | 8 | 34 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/matd3/mpe/simple_push_v3.yaml | YAML | 25 | 0 | 7 | 32 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/matd3/mpe/simple_spread_v3.yaml | YAML | 25 | 0 | 7 | 32 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mfac/mpe/simple_spread_v3.yaml | YAML | 32 | 1 | 7 | 40 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mfq/magent2/adversarial_pursuit_v4.yaml | YAML | 43 | 1 | 6 | 50 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mfq/mpe/simple_spread_v3.yaml | YAML | 25 | 0 | 6 | 31 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/mpdqn/Platform.yaml | YAML | 25 | 0 | 7 | 32 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/atari.yaml | YAML | 38 | 1 | 7 | 46 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/box2d/CarRacing-v2.yaml | YAML | 32 | 1 | 7 | 40 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/box2d/LunarLander-v2.yaml | YAML | 30 | 0 | 6 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/classic_control/Acrobot-v1.yaml | YAML | 30 | 0 | 6 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/classic_control/CartPole-v1.yaml | YAML | 30 | 0 | 6 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/noisydqn/classic_control/MountainCar-v0.yaml | YAML | 30 | 0 | 6 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pdqn/Platform.yaml | YAML | 25 | 0 | 7 | 32 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/atari.yaml | YAML | 40 | 1 | 8 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/box2d/CarRacing-v2.yaml | YAML | 34 | 1 | 8 | 43 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/box2d/LunarLander-v2.yaml | YAML | 32 | 0 | 7 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/classic_control/Acrobot-v1.yaml | YAML | 32 | 0 | 7 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/classic_control/CartPole-v1.yaml | YAML | 32 | 0 | 7 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/perdqn/classic_control/MountainCar-v1.yaml | YAML | 32 | 0 | 7 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/box2d/BipedalWalker-v3.yaml | YAML | 31 | 0 | 5 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/box2d/LunarLander-v2.yaml | YAML | 31 | 0 | 5 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/classic_control/Acrobot-v1.yaml | YAML | 31 | 0 | 5 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/classic_control/CartPole-v1.yaml | YAML | 31 | 0 | 5 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/classic_control/MountainCar-v0.yaml | YAML | 31 | 0 | 6 | 37 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/classic_control/Pendulum-v1.yaml | YAML | 31 | 0 | 5 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/pg/mujoco.yaml | YAML | 31 | 0 | 5 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/box2d/BipedalWalker-v3.yaml | YAML | 35 | 0 | 6 | 41 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/box2d/LunarLander-v2.yaml | YAML | 35 | 0 | 5 | 40 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/classic_control/Acrobot-v1.yaml | YAML | 35 | 0 | 6 | 41 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/classic_control/CartPole-v1.yaml | YAML | 35 | 0 | 5 | 40 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/classic_control/MountainCar-v0.yaml | YAML | 35 | 0 | 6 | 41 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/classic_control/Pendulum-v1.yaml | YAML | 35 | 0 | 6 | 41 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppg/mujoco.yaml | YAML | 35 | 0 | 7 | 42 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/atari.yaml | YAML | 43 | 1 | 7 | 51 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/box2d/BipedalWalker-v3.yaml | YAML | 35 | 0 | 6 | 41 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/box2d/CarRacing-v2.yaml | YAML | 37 | 1 | 6 | 44 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/box2d/LunarLander-v2.yaml | YAML | 35 | 0 | 6 | 41 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/classic_control/Acrobot-v1.yaml | YAML | 35 | 0 | 7 | 42 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/classic_control/CartPole-v1.yaml | YAML | 35 | 0 | 7 | 42 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/classic_control/MountainCar-v0.yaml | YAML | 35 | 0 | 7 | 42 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/classic_control/Pendulum-v1.yaml | YAML | 35 | 0 | 7 | 42 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/ppo/mujoco.yaml | YAML | 35 | 0 | 7 | 42 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/mpe/simple_spread_v3.yaml | YAML | 37 | 0 | 7 | 44 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/25m.yaml | YAML | 43 | 1 | 8 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/2m_vs_1z.yaml | YAML | 43 | 1 | 8 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/3m.yaml | YAML | 43 | 1 | 8 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/5m_vs_6m.yaml | YAML | 43 | 1 | 8 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/8m.yaml | YAML | 43 | 1 | 8 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/8m_vs_9m.yaml | YAML | 43 | 1 | 8 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/MMM2.yaml | YAML | 43 | 1 | 8 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qmix/sc2/corridor.yaml | YAML | 43 | 1 | 8 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/atari.yaml | YAML | 39 | 1 | 7 | 47 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/box2d/CarRacing-v2.yaml | YAML | 33 | 1 | 7 | 41 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/box2d/LunarLander-v2.yaml | YAML | 31 | 0 | 6 | 37 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/classic_control/Acrobot-v1.yaml | YAML | 31 | 0 | 6 | 37 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/classic_control/CartPole-v1.yaml | YAML | 31 | 0 | 6 | 37 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qrdqn/classic_control/MountainCar-v0.yaml | YAML | 31 | 0 | 6 | 37 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/qtran/mpe/simple_spread_v3.yaml | YAML | 28 | 0 | 6 | 34 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/random/mpe/simple_adversary.yaml | YAML | 7 | 0 | 1 | 8 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/random/mpe/simple_push.yaml | YAML | 7 | 0 | 1 | 8 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/random/mpe/simple_spread.yaml | YAML | 7 | 0 | 1 | 8 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/atari.yaml | YAML | 41 | 0 | 6 | 47 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/box2d/BipedalWalker-v3.yaml | YAML | 31 | 0 | 6 | 37 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/box2d/LunarLander-v2.yaml | YAML | 32 | 0 | 6 | 38 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/classic_control/Acrobot-v1.yaml | YAML | 32 | 0 | 6 | 38 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/classic_control/CartPole-v1.yaml | YAML | 32 | 0 | 6 | 38 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/classic_control/MountainCar-v0.yaml | YAML | 32 | 0 | 6 | 38 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/classic_control/Pendulum-v1.yaml | YAML | 31 | 0 | 6 | 37 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/sac/mujoco.yaml | YAML | 33 | 0 | 6 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/spdqn/Platform-v0.yaml | YAML | 25 | 0 | 7 | 32 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/td3/box2d/BipedalWalker-v3.yaml | YAML | 31 | 0 | 5 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/td3/classic_control/Pendulum-v1.yaml | YAML | 31 | 0 | 5 | 36 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/td3/mujoco.yaml | YAML | 31 | 0 | 6 | 37 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdac/mpe/simple_spread_v3.yaml | YAML | 41 | 1 | 8 | 50 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/football/3v1.yaml | YAML | 49 | 2 | 7 | 58 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/mpe/simple_spread_v3.yaml | YAML | 35 | 0 | 6 | 41 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/25m.yaml | YAML | 41 | 1 | 7 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/2m_vs_1z.yaml | YAML | 41 | 1 | 7 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/3m.yaml | YAML | 41 | 1 | 7 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/5m_vs_6m.yaml | YAML | 41 | 1 | 7 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/8m.yaml | YAML | 41 | 1 | 7 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/8m_vs_9m.yaml | YAML | 41 | 1 | 7 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/MMM2.yaml | YAML | 41 | 1 | 7 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/vdn/sc2/corridor.yaml | YAML | 41 | 1 | 7 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/mpe/simple_spread_v3.yaml | YAML | 38 | 0 | 6 | 44 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/25m.yaml | YAML | 44 | 1 | 9 | 54 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/2m_vs_1z.yaml | YAML | 44 | 1 | 9 | 54 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/3m.yaml | YAML | 44 | 1 | 9 | 54 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/5m_vs_6m.yaml | YAML | 44 | 1 | 9 | 54 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/8m.yaml | YAML | 44 | 1 | 9 | 54 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/8m_vs_9m.yaml | YAML | 44 | 1 | 9 | 54 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/MMM2.yaml | YAML | 44 | 1 | 9 | 54 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/configs/wqmix/sc2/corridor.yaml | YAML | 44 | 1 | 9 | 54 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/__init__.py | Python | 60 | 0 | 8 | 68 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/football/__init__.py | Python | 20 | 19 | 2 | 41 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/football/gfootball_env.py | Python | 64 | 0 | 10 | 74 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/football/gfootball_vec_env.py | Python | 81 | 0 | 9 | 90 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/football/raw_env.py | Python | 90 | 2 | 11 | 103 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/gym/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/gym/gym_env.py | Python | 180 | 41 | 33 | 254 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/gym/gym_vec_env.py | Python | 196 | 17 | 28 | 241 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/__init__.py | Python | 19 | 1 | 7 | 27 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/build.sh | Shell Script | 13 | 3 | 3 | 19 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/battle.py | Python | 31 | 2 | 10 | 43 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/double_attack.py | Python | 41 | 4 | 11 | 56 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/forest.py | Python | 41 | 1 | 10 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/builtin/config/pursuit.py | Python | 34 | 0 | 10 | 44 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/c_lib.py | Python | 26 | 5 | 13 | 44 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environment.py | Python | 25 | 4 | 15 | 44 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/__init__.py | Python | 3 | 0 | 3 | 6 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/adversarial_pursuit/__init__.py | Python | 1 | 0 | 1 | 2 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/adversarial_pursuit/adversarial_pursuit.py | Python | 130 | 100 | 26 | 256 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/adversarial_pursuit_v4.py | Python | 5 | 0 | 1 | 6 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battle/__init__.py | Python | 1 | 0 | 1 | 2 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battle/battle.py | Python | 164 | 115 | 27 | 306 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battle_v4.py | Python | 1 | 0 | 1 | 2 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battlefield/__init__.py | Python | 1 | 0 | 1 | 2 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battlefield/battlefield.py | Python | 146 | 116 | 26 | 288 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/battlefield_v5.py | Python | 1 | 0 | 1 | 2 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/combined_arms/__init__.py | Python | 1 | 0 | 1 | 2 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/combined_arms/combined_arms.py | Python | 259 | 118 | 38 | 415 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/combined_arms_v6.py | Python | 1 | 0 | 1 | 2 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/gather/__init__.py | Python | 1 | 0 | 1 | 2 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/gather/gather.py | Python | 186 | 105 | 33 | 324 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/gather_v5.py | Python | 1 | 0 | 1 | 2 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/magent_env.py | Python | 247 | 6 | 38 | 291 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/tiger_deer/__init__.py | Python | 1 | 0 | 1 | 2 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/tiger_deer/tiger_deer.py | Python | 141 | 88 | 28 | 257 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/environments/tiger_deer_v4.py | Python | 1 | 0 | 1 | 2 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/gridworld.py | Python | 531 | 287 | 98 | 916 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/magent_env.py | Python | 58 | 0 | 12 | 70 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/magent_vec_env.py | Python | 124 | 7 | 23 | 154 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/render.py | Python | 289 | 2 | 47 | 338 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/magent2/utility.py | Python | 81 | 16 | 23 | 120 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/pettingzoo/__init__.py | Python | 23 | 0 | 2 | 25 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/pettingzoo/pettingzoo_env.py | Python | 90 | 3 | 17 | 110 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/pettingzoo/pettingzoo_vec_env.py | Python | 130 | 5 | 22 | 157 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/starcraft2/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/starcraft2/sc2_env.py | Python | 54 | 0 | 11 | 65 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/starcraft2/sc2_vec_env.py | Python | 261 | 12 | 30 | 303 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/vector_envs/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/vector_envs/env_utils.py | Python | 100 | 11 | 26 | 137 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/vector_envs/subproc_vec_env.py | Python | 132 | 18 | 26 | 176 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/environment/vector_envs/vector_env.py | Python | 60 | 28 | 16 | 104 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/__init__.py | Python | 111 | 0 | 6 | 117 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/agent.py | Python | 39 | 0 | 10 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/agents_marl.py | Python | 88 | 0 | 18 | 106 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/coma_agents.py | Python | 90 | 1 | 13 | 104 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/dcg_agents.py | Python | 86 | 0 | 12 | 98 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/iddpg_agents.py | Python | 80 | 0 | 11 | 91 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/iql_agents.py | Python | 71 | 0 | 13 | 84 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/isac_agents.py | Python | 79 | 0 | 11 | 90 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/maddpg_agents.py | Python | 80 | 0 | 11 | 91 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/mappoclip_agents.py | Python | 83 | 0 | 14 | 97 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/mappokl_agents.py | Python | 84 | 1 | 14 | 99 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/masac_agents.py | Python | 79 | 0 | 11 | 90 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/matd3_agents.py | Python | 84 | 0 | 12 | 96 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/mfac_agents.py | Python | 93 | 1 | 16 | 110 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/mfq_agents.py | Python | 97 | 0 | 13 | 110 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/qmix_agents.py | Python | 73 | 0 | 12 | 85 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/qtran_agents.py | Python | 81 | 0 | 13 | 94 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/vdac_agents.py | Python | 91 | 0 | 14 | 105 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/vdn_agents.py | Python | 72 | 0 | 12 | 84 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/multi_agent_rl/wqmix_agents.py | Python | 76 | 0 | 12 | 88 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/a2c_agent.py | Python | 128 | 0 | 15 | 143 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/ddpg_agent.py | Python | 122 | 0 | 14 | 136 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/mpdqn_agent.py | Python | 165 | 1 | 19 | 185 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/pdqn_agent.py | Python | 153 | 1 | 18 | 172 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/pg_agent.py | Python | 125 | 0 | 15 | 140 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/ppg_agent.py | Python | 145 | 5 | 19 | 169 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/ppoclip_agent.py | Python | 129 | 0 | 17 | 146 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/ppokl_agent.py | Python | 129 | 0 | 17 | 146 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/sac_agent.py | Python | 121 | 0 | 17 | 138 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/sacdis_agent.py | Python | 120 | 2 | 17 | 139 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/spdqn_agent.py | Python | 172 | 1 | 20 | 193 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/policy_gradient/td3_agent.py | Python | 123 | 0 | 14 | 137 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/C51_agent.py | Python | 125 | 1 | 20 | 146 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/cdqn_agent.py | Python | 125 | 1 | 20 | 146 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/cldqn_agent.py | Python | 125 | 1 | 20 | 146 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/ddqn_agent.py | Python | 125 | 1 | 20 | 146 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/dqn_agent.py | Python | 125 | 1 | 20 | 146 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/dueldqn_agent.py | Python | 126 | 1 | 20 | 147 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/ldqn_agent.py | Python | 125 | 1 | 20 | 146 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/noisydqn_agent.py | Python | 124 | 1 | 21 | 146 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/perdqn_agent.py | Python | 130 | 1 | 22 | 153 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/agents/qlearning_family/qrdqn_agent.py | Python | 125 | 1 | 20 | 146 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/__init__.py | Python | 49 | 0 | 4 | 53 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/learner.py | Python | 87 | 1 | 12 | 100 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/coma_learner.py | Python | 118 | 9 | 17 | 144 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/dcg_learner.py | Python | 138 | 10 | 17 | 165 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/iddpg_learner.py | Python | 75 | 7 | 11 | 93 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/iql_learner.py | Python | 56 | 8 | 8 | 72 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/isac_learner.py | Python | 84 | 7 | 13 | 104 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/maddpg_learner.py | Python | 80 | 10 | 10 | 100 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/mappoclip_learner.py | Python | 77 | 8 | 12 | 97 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/mappokl_learner.py | Python | 82 | 13 | 12 | 107 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/masac_learner.py | Python | 84 | 7 | 12 | 103 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/matd3_learner.py | Python | 104 | 7 | 13 | 124 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/mfac_learner.py | Python | 103 | 10 | 14 | 127 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/mfq_learner.py | Python | 65 | 7 | 10 | 82 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/qmix_learner.py | Python | 61 | 8 | 9 | 78 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/qtran_learner.py | Python | 98 | 7 | 14 | 119 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/vdac_learner.py | Python | 50 | 6 | 10 | 66 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/vdn_learner.py | Python | 60 | 9 | 8 | 77 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/multi_agent_rl/wqmix_learner.py | Python | 84 | 12 | 12 | 108 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/a2c_learner.py | Python | 46 | 7 | 9 | 62 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/ddpg_learner.py | Python | 56 | 2 | 11 | 69 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/mpdqn_learner.py | Python | 81 | 6 | 14 | 101 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/pdqn_learner.py | Python | 61 | 6 | 12 | 79 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/pg_learner.py | Python | 40 | 4 | 8 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/ppg_learner.py | Python | 79 | 4 | 11 | 94 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/ppoclip_learner.py | Python | 51 | 8 | 7 | 66 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/ppokl_learner.py | Python | 51 | 2 | 7 | 60 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/sac_learner.py | Python | 55 | 1 | 12 | 68 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/sacdis_learner.py | Python | 61 | 2 | 12 | 75 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/spdqn_learner.py | Python | 82 | 6 | 14 | 102 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/policy_gradient/td3_learner.py | Python | 60 | 7 | 11 | 78 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/c51_learner.py | Python | 59 | 4 | 15 | 78 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/cdqn_learner.py | Python | 45 | 5 | 10 | 60 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/cldqn_learner.py | Python | 45 | 5 | 10 | 60 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/ddqn_learner.py | Python | 48 | 2 | 11 | 61 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/dqn_learner.py | Python | 45 | 5 | 10 | 60 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/dueldqn_learner.py | Python | 45 | 2 | 10 | 57 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/ldqn_learner.py | Python | 45 | 5 | 10 | 60 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/perdqn_learner.py | Python | 50 | 5 | 13 | 68 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/learners/qlearning_family/qrdqn_learner.py | Python | 54 | 5 | 11 | 70 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/__init__.py | Python | 150 | 3 | 8 | 161 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/categorical.py | Python | 201 | 60 | 42 | 303 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/categorical_marl.py | Python | 252 | 1 | 39 | 292 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/deterministic.py | Python | 716 | 20 | 108 | 844 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/deterministic_marl.py | Python | 440 | 3 | 70 | 513 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/gaussian.py | Python | 207 | 12 | 35 | 254 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/gaussian_marl.py | Python | 247 | 5 | 43 | 295 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/policies/mixers.py | Python | 195 | 8 | 29 | 232 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/representations/__init__.py | Python | 35 | 0 | 4 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/representations/networks.py | Python | 266 | 5 | 44 | 315 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/runners/__init__.py | Python | 7 | 0 | 2 | 9 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/runners/runner_basic.py | Python | 85 | 2 | 16 | 103 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/runners/runner_drl.py | Python | 71 | 0 | 8 | 79 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/runners/runner_marl.py | Python | 105 | 3 | 18 | 126 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/__init__.py | Python | 2 | 0 | 0 | 2 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/distributions.py | Python | 46 | 0 | 18 | 64 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/input_reformat.py | Python | 83 | 0 | 11 | 94 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/layers.py | Python | 90 | 0 | 12 | 102 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/operations.py | Python | 47 | 0 | 12 | 59 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/mindspore/utils/set_trainer.py | Python | 32 | 0 | 7 | 39 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/__init__.py | Python | 109 | 4 | 9 | 122 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/agent.py | Python | 114 | 6 | 17 | 137 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/agents_marl.py | Python | 83 | 2 | 17 | 102 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/coma_agents.py | Python | 65 | 2 | 10 | 77 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/dcg_agents.py | Python | 89 | 2 | 12 | 103 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/iddpg_agents.py | Python | 82 | 0 | 11 | 93 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/iql_agents.py | Python | 73 | 2 | 11 | 86 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/isac_agents.py | Python | 81 | 0 | 11 | 92 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/maddpg_agents.py | Python | 83 | 0 | 11 | 94 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/mappoclip_agents.py | Python | 86 | 0 | 14 | 100 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/mappokl_agents.py | Python | 85 | 0 | 14 | 99 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/masac_agents.py | Python | 81 | 0 | 11 | 92 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/matd3_agents.py | Python | 83 | 0 | 11 | 94 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/mfac_agents.py | Python | 90 | 0 | 16 | 106 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/mfq_agents.py | Python | 98 | 0 | 12 | 110 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/qmix_agents.py | Python | 76 | 2 | 11 | 89 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/qtran_agents.py | Python | 83 | 2 | 12 | 97 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/vdac_agents.py | Python | 94 | 0 | 14 | 108 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/vdn_agents.py | Python | 75 | 2 | 11 | 88 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/multi_agent_rl/wqmix_agents.py | Python | 78 | 2 | 11 | 91 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/a2c_agent.py | Python | 125 | 1 | 18 | 144 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/ddpg_agent.py | Python | 111 | 1 | 18 | 130 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/mpdqn_agent.py | Python | 161 | 0 | 19 | 180 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/pdqn_agent.py | Python | 159 | 0 | 19 | 178 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/pg_agent.py | Python | 125 | 1 | 19 | 145 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/ppg_agent.py | Python | 128 | 4 | 19 | 151 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/ppoclip_agent.py | Python | 127 | 1 | 18 | 146 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/ppokl_agent.py | Python | 122 | 1 | 18 | 141 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/sac_agent.py | Python | 108 | 1 | 19 | 128 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/sacdis_agent.py | Python | 115 | 2 | 16 | 133 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/spdqn_agent.py | Python | 165 | 0 | 19 | 184 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/policy_gradient/td3_agent.py | Python | 112 | 1 | 18 | 131 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/c51_agent.py | Python | 117 | 2 | 19 | 138 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/ddqn_agent.py | Python | 117 | 2 | 19 | 138 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/dqn_agent.py | Python | 117 | 2 | 18 | 137 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/drqn_agent.py | Python | 131 | 2 | 18 | 151 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/dueldqn_agent.py | Python | 117 | 2 | 19 | 138 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/noisydqn_agent.py | Python | 116 | 2 | 19 | 137 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/perdqn_agent.py | Python | 123 | 2 | 20 | 145 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/agents/qlearning_family/qrdqn_agent.py | Python | 117 | 2 | 19 | 138 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/__init__.py | Python | 47 | 0 | 4 | 51 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/learner.py | Python | 66 | 2 | 12 | 80 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/coma_learner.py | Python | 115 | 8 | 17 | 140 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/dcg_learner.py | Python | 155 | 11 | 20 | 186 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/iddpg_learner.py | Python | 77 | 7 | 12 | 96 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/iql_learner.py | Python | 58 | 5 | 12 | 75 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/isac_learner.py | Python | 82 | 5 | 13 | 100 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/maddpg_learner.py | Python | 77 | 9 | 12 | 98 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/mappoclip_learner.py | Python | 77 | 7 | 12 | 96 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/mappokl_learner.py | Python | 86 | 7 | 14 | 107 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/masac_learner.py | Python | 82 | 5 | 13 | 100 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/matd3_learner.py | Python | 83 | 6 | 11 | 100 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/mfac_learner.py | Python | 91 | 11 | 14 | 116 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/mfq_learner.py | Python | 73 | 8 | 13 | 94 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/qmix_learner.py | Python | 61 | 7 | 11 | 79 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/qtran_learner.py | Python | 92 | 8 | 12 | 112 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/vdac_learner.py | Python | 64 | 6 | 12 | 82 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/vdn_learner.py | Python | 59 | 6 | 12 | 77 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/multi_agent_rl/wqmix_learner.py | Python | 83 | 11 | 14 | 108 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/a2c_learner.py | Python | 43 | 0 | 9 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/ddpg_learner.py | Python | 63 | 2 | 12 | 77 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/mpdqn_learner.py | Python | 68 | 2 | 12 | 82 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/pdqn_learner.py | Python | 68 | 2 | 12 | 82 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/pg_learner.py | Python | 37 | 0 | 11 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/ppg_learner.py | Python | 95 | 1 | 15 | 111 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/ppoclip_learner.py | Python | 47 | 1 | 8 | 56 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/ppokl_learner.py | Python | 56 | 1 | 9 | 66 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/sac_learner.py | Python | 65 | 3 | 12 | 80 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/sacdis_learner.py | Python | 69 | 3 | 12 | 84 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/spdqn_learner.py | Python | 72 | 2 | 12 | 86 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/policy_gradient/td3_learner.py | Python | 63 | 6 | 11 | 80 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/c51_learner.py | Python | 41 | 0 | 13 | 54 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/cdqn_learner.py | Python | 38 | 1 | 8 | 47 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/cldqn_learner.py | Python | 40 | 1 | 8 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/ddqn_learner.py | Python | 40 | 1 | 9 | 50 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/dqn_learner.py | Python | 41 | 0 | 8 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/drqn_learner.py | Python | 44 | 2 | 11 | 57 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/dueldqn_learner.py | Python | 39 | 1 | 8 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/ldqn_learner.py | Python | 39 | 1 | 8 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/perdqn_learner.py | Python | 41 | 1 | 9 | 51 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/learners/qlearning_family/qrdqn_learner.py | Python | 39 | 1 | 7 | 47 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/__init__.py | Python | 166 | 3 | 9 | 178 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/categorical.py | Python | 195 | 3 | 31 | 229 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/categorical_marl.py | Python | 253 | 1 | 30 | 284 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/deterministic.py | Python | 706 | 0 | 97 | 803 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/deterministic_marl.py | Python | 680 | 26 | 81 | 787 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/gaussian.py | Python | 215 | 2 | 32 | 249 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/gaussian_marl.py | Python | 215 | 3 | 29 | 247 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/policies/mixers.py | Python | 204 | 8 | 32 | 244 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/representations/__init__.py | Python | 40 | 0 | 5 | 45 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/representations/networks.py | Python | 288 | 1 | 46 | 335 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/runners/__init__.py | Python | 7 | 0 | 2 | 9 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/runners/runner_basic.py | Python | 126 | 3 | 19 | 148 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/runners/runner_drl.py | Python | 103 | 9 | 16 | 128 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/runners/runner_marl.py | Python | 105 | 3 | 18 | 126 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/__init__.py | Python | 3 | 0 | 0 | 3 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/distributions.py | Python | 70 | 0 | 28 | 98 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/input_reformat.py | Python | 82 | 0 | 12 | 94 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/layers.py | Python | 107 | 0 | 13 | 120 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/tensorflow/utils/operations.py | Python | 51 | 3 | 17 | 71 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/__init__.py | Python | 104 | 0 | 6 | 110 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/agent.py | Python | 115 | 6 | 17 | 138 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/agents_marl.py | Python | 72 | 3 | 15 | 90 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/coma_agents.py | Python | 77 | 4 | 11 | 92 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/dcg_agents.py | Python | 99 | 0 | 11 | 110 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/iddpg_agents.py | Python | 58 | 0 | 6 | 64 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/iql_agents.py | Python | 81 | 0 | 11 | 92 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/isac_agents.py | Python | 57 | 0 | 7 | 64 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/maddpg_agents.py | Python | 57 | 0 | 7 | 64 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/mappo_agents.py | Python | 102 | 4 | 11 | 117 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/masac_agents.py | Python | 57 | 0 | 8 | 65 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/matd3_agents.py | Python | 61 | 0 | 7 | 68 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/mfac_agents.py | Python | 73 | 0 | 11 | 84 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/mfq_agents.py | Python | 77 | 0 | 10 | 87 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/qmix_agents.py | Python | 84 | 0 | 11 | 95 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/qtran_agents.py | Python | 58 | 0 | 9 | 67 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/vdac_agents.py | Python | 69 | 0 | 10 | 79 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/vdn_agents.py | Python | 83 | 0 | 11 | 94 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/multi_agent_rl/wqmix_agents.py | Python | 86 | 0 | 11 | 97 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/a2c_agent.py | Python | 144 | 1 | 17 | 162 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/ddpg_agent.py | Python | 116 | 1 | 18 | 135 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/mpdqn_agent.py | Python | 159 | 0 | 19 | 178 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/pdqn_agent.py | Python | 158 | 0 | 20 | 178 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/pg_agent.py | Python | 134 | 1 | 15 | 150 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/ppg_agent.py | Python | 149 | 4 | 18 | 171 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/ppoclip_agent.py | Python | 148 | 1 | 19 | 168 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/ppokl_agent.py | Python | 146 | 1 | 18 | 165 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/sac_agent.py | Python | 112 | 1 | 19 | 132 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/sacdis_agent.py | Python | 119 | 1 | 16 | 136 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/spdqn_agent.py | Python | 157 | 0 | 19 | 176 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/policy_gradient/td3_agent.py | Python | 116 | 1 | 18 | 135 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/c51_agent.py | Python | 121 | 2 | 19 | 142 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/ddqn_agent.py | Python | 122 | 2 | 18 | 142 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/dqn_agent.py | Python | 121 | 2 | 18 | 141 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/drqn_agent.py | Python | 138 | 2 | 20 | 160 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/dueldqn_agent.py | Python | 122 | 2 | 19 | 143 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/noisydqn_agent.py | Python | 122 | 2 | 19 | 143 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/perdqn_agent.py | Python | 128 | 2 | 20 | 150 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/agents/qlearning_family/qrdqn_agent.py | Python | 122 | 2 | 19 | 143 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/__init__.py | Python | 43 | 1 | 4 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/learner.py | Python | 79 | 0 | 17 | 96 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/coma_learner.py | Python | 98 | 8 | 16 | 122 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/dcg_learner.py | Python | 188 | 8 | 22 | 218 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/iddpg_learner.py | Python | 64 | 5 | 11 | 80 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/iql_learner.py | Python | 104 | 9 | 21 | 134 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/isac_learner.py | Python | 70 | 6 | 11 | 87 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/maddpg_learner.py | Python | 67 | 9 | 10 | 86 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/mappo_learner.py | Python | 178 | 14 | 20 | 212 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/masac_learner.py | Python | 70 | 6 | 11 | 87 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/matd3_learner.py | Python | 76 | 6 | 9 | 91 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/mfac_learner.py | Python | 80 | 10 | 13 | 103 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/mfq_learner.py | Python | 57 | 7 | 11 | 75 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/qmix_learner.py | Python | 111 | 11 | 18 | 140 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/qtran_learner.py | Python | 84 | 8 | 11 | 103 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/vdac_learner.py | Python | 50 | 6 | 10 | 66 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/vdn_learner.py | Python | 108 | 14 | 18 | 140 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/multi_agent_rl/wqmix_learner.py | Python | 168 | 19 | 23 | 210 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/a2c_learner.py | Python | 41 | 1 | 9 | 51 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/ddpg_learner.py | Python | 44 | 3 | 10 | 57 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/mpdqn_learner.py | Python | 46 | 2 | 12 | 60 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/pdqn_learner.py | Python | 46 | 2 | 19 | 67 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/pg_learner.py | Python | 35 | 1 | 9 | 45 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/ppg_learner.py | Python | 78 | 2 | 11 | 91 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/ppoclip_learner.py | Python | 54 | 2 | 10 | 66 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/ppokl_learner.py | Python | 52 | 2 | 9 | 63 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/sac_learner.py | Python | 44 | 3 | 10 | 57 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/sacdis_learner.py | Python | 50 | 5 | 10 | 65 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/spdqn_learner.py | Python | 46 | 2 | 12 | 60 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/policy_gradient/td3_learner.py | Python | 49 | 6 | 9 | 64 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/c51_learner.py | Python | 41 | 1 | 9 | 51 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/ddqn_learner.py | Python | 39 | 1 | 11 | 51 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/dqn_learner.py | Python | 38 | 1 | 9 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/drqn_learner.py | Python | 42 | 2 | 11 | 55 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/dueldqn_learner.py | Python | 38 | 1 | 9 | 48 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/perdqn_learner.py | Python | 39 | 1 | 9 | 49 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/qlearning_family/qrdqn_learner.py | Python | 37 | 1 | 8 | 46 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/ssl_rl/__init__.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/learners/ssl_rl/curl_learner.py | Python | 0 | 0 | 1 | 1 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/__init__.py | Python | 159 | 3 | 8 | 170 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/categorical.py | Python | 208 | 7 | 34 | 249 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/categorical_marl.py | Python | 222 | 6 | 28 | 256 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/coordination_graph.py | Python | 68 | 1 | 9 | 78 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/deterministic.py | Python | 743 | 2 | 97 | 842 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/deterministic_marl.py | Python | 504 | 4 | 64 | 572 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/gaussian.py | Python | 217 | 2 | 31 | 250 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/gaussian_marl.py | Python | 188 | 4 | 31 | 223 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/policies/mixers.py | Python | 117 | 6 | 19 | 142 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/representations/__init__.py | Python | 38 | 0 | 6 | 44 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/representations/cnn.py | Python | 83 | 1 | 10 | 94 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/representations/mlp.py | Python | 42 | 2 | 8 | 52 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/representations/rnn.py | Python | 71 | 0 | 8 | 79 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/__init__.py | Python | 13 | 0 | 2 | 15 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_basic.py | Python | 11 | 2 | 6 | 19 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_drl.py | Python | 119 | 3 | 14 | 136 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_football.py | Python | 102 | 5 | 18 | 125 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_magent.py | Python | 5 | 0 | 3 | 8 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_pettingzoo.py | Python | 339 | 11 | 43 | 393 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/runners/runner_sc2.py | Python | 319 | 13 | 39 | 371 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/__init__.py | Python | 22 | 0 | 4 | 26 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/distributions.py | Python | 72 | 0 | 29 | 101 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/input_reformat.py | Python | 104 | 0 | 15 | 119 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/layers.py | Python | 101 | 0 | 12 | 113 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/operations.py | Python | 86 | 0 | 18 | 104 | -| /home/wzliu/PCNL_XuanCe/XuanPolicy_Library/xuanpolicy/xuanpolicy/torch/utils/value_norm.py | Python | 54 | 3 | 20 | 77 | -| Total | | 43,396 | 2,416 | 6,986 | 52,798 | -+----------------------------------------------------------------------------------------------------------------------------------------------+--------------+------------+------------+------------+------------+ \ No newline at end of file diff --git a/xuanpolicy/__init__.py b/xuanpolicy/__init__.py deleted file mode 100644 index d97cd75c9..000000000 --- a/xuanpolicy/__init__.py +++ /dev/null @@ -1,5 +0,0 @@ -from xuanpolicy import common, environment, configs -from xuanpolicy import tensorflow, mindspore, torch -from xuanpolicy.common.common_tools import get_runner, get_arguments - -__version__ = '0.1.11' \ No newline at end of file diff --git a/xuanpolicy/common/__init__.py b/xuanpolicy/common/__init__.py deleted file mode 100644 index 434c570ff..000000000 --- a/xuanpolicy/common/__init__.py +++ /dev/null @@ -1,5 +0,0 @@ -from xuanpolicy.common.common_tools import * -from xuanpolicy.common.statistic_tools import * -from xuanpolicy.common.memory_tools import * -from xuanpolicy.common.memory_tools_marl import * -from xuanpolicy.common.segtree_tool import * diff --git a/xuanpolicy/environment/magent2/build.sh b/xuanpolicy/environment/magent2/build.sh deleted file mode 100755 index e1b13616a..000000000 --- a/xuanpolicy/environment/magent2/build.sh +++ /dev/null @@ -1,18 +0,0 @@ -#!/bin/bash -if [ $1 ] && [ $1 = '-c' ] # clean -then - rm -rf *.log save_model build -fi - -mkdir -p build -cd build -touch __init__.py -cmake .. - -if [[ "$OSTYPE" == "linux-gnu" ]]; then - # Linux - make -j `nproc` -elif [[ "$OSTYPE" == "darwin"* ]]; then - # Mac OSX - make -j `sysctl -n hw.ncpu` -fi