用深度强化学习打乒乓 https://github.com/mtrazzi/spinning-up-a-Pong-AI-with-deep-RL
可复现强化学习研究框架 https://github.com/rlworkgroup/garage
深度强化学习教程(高质量PyTorch实现集锦) https://github.com/qfettes/DeepRL-Tutorials
BabyAI: First Steps Towards Grounded Language Learning With a Human In the Loop https://github.com/mila-udem/babyai
PaddlePaddle强化学习框架 https://github.com/PaddlePaddle/PARL
【Catalyst深度学习/强化学习框架实例入门】《Beyond fashion: Deep Learning with Catalyst》 https://evilmartians.com/chronicles/beyond-fashion-deep-learning-with-catalyst
Random Network Distillation(PyTorch) https://github.com/jcwleo/random-network-distillation-pytorch
A collection of Reinforcement Learning algorithms from Sutton and Barto's book and other research papers implemented in Python. https://github.com/Pulkit-Khandelwal/Reinforcement-Learning-Notebooks
Leela Zero围棋程序界面 https://github.com/featurecat/lizzie
【用强化学习玩飞翔小鸟】’FlapAI-Bird - An AI program that plays Flappy Bird using reinforcement learning.' https://github.com/taivu1998/FlapAI-Bird
【用Deep Q-learning玩俄罗斯方块】’[PYTORCH] Deep Q-learning for playing Tetris - Deep Q-learning for playing tetris game' https://github.com/uvipen/Tetris-deep-Q-learning-pytorch
【Tianshou (天授)：优雅、灵活、超快的PyTorch深度强化学习平台】 https://github.com/thu-ml/tianshou
AlphaZero算法的简单、快速实现 https://github.com/jonathan-laurent/AlphaZero.jl
https://github.com/mtrazzi/rl-book-challenge
Catalyst(PyTorch深度学习/强化学习研究框架)相关资源大列表 https://github.com/catalyst-team/awesome-catalyst-list
OpenAI发布的深度强化学习教学资源集(教程、代码、习题、文档等) https://github.com/openai/spinningup
用Keras自己打造AlphaZero AI https://github.com/AppliedDataSciencePartners/DeepReinforcementLearning
训练一个神经网络来玩贪食蛇 https://github.com/greerviau/SnakeAI
英文）OpenAI 制作的教育资源，可以更容易地学习深层强化学习。官方项目，浅显易懂，提供练手的例子，方便初学者或对深层强化学习感兴趣的人群学习和入门 https://github.com/openai/spinningup
PyTorch的深度强化学习算法，Deep Reinforcement Learning Algorithms with PyTorch https://github.com/p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch
PyTorch实现的深度强化学习算法：DQN, AC, ACER, A2C, A3C, , PG, DDPG, TRPO, PPO… https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch
Learning to Learn how to Learn: Self-Adaptive Visual Navigation using Meta-Learning https://github.com/allenai/savn
一个DeepMind开放的增强学习的开源工具库，Open sourcing TRFL: a library of reinforcement learning building blocks https://github.com/deepmind/trfl/
https://github.com/victorqribeiro/bangBangML
PRL：新开源强化学习框架 https://github.com/opium-sh/prl
【smarties：轻量可扩展的强化学习框架】 https://github.com/cselab/smarties
中国象棋Zero（CCZero）：用AlphaZero/AlphaGo Zero类似算法训练的中国象棋机器人 https://github.com/NeymarL/ChineseChess-AlphaZero
OpenSpiel游戏强化学习框架：包含一系列环境、算法，用于研究一般强化学习和游戏中的搜索/规划 https://github.com/deepmind/open_spiel
Real-Time Reinforcement Learning https://github.com/rmst/rtrl
多智能体强化学习环境 https://github.com/Bigpig4396/Multi-Agent-Reinforcement-Learning-Environment
Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software https://www.arxiv-vanity.com/papers/1912.07833/
“强化学习：过去、现在和未来(NeurIPS 2019)” https://www.bilibili.com/video/av79448071?p=8
'State-of-the-art Model-free Reinforcement Learning Algorithms - PyTorch implementation of Soft Actor-Critic (SAC), Twin Delayed DDPG (TD3), Actor-Critic (AC/A2C), Proximal Policy Optimization (PPO), QT-Opt, PointNet..' https://github.com/quantumiracle/SOTA-RL-Algorithms
《DeepRacer: Educational Autonomous Racing Platform for Experimentation with Sim2Real Reinforcement Learning》 https://github.com/awslabs/amazon-sagemaker-examples/tree/master/reinforcement_learning/rl_deepracer_robomaker_coach_gazebo
RLCard：纸牌游戏强化学习工具包 https://github.com/datamllab/rlcard
一个深度强化学习项目，研究如何让机器用画笔画画。也可体验制作自己的绘画或根据一张图片生成一整个绘画过程 https://github.com/hzwer/ICCV2019-LearningToPaint
深度强化学习基础——理论与Python实战 https://github.com/kengz/SLM-Lab
【《强化学习导论(第二版)》的Python实现】 https://github.com/JaeDukSeo/reinforcement-learning-an-introduction
【BigTransfer (BiT)：最先进的计算机视觉强化学习】《BigTransfer (BiT): State-of-the-art transfer learning for computer vision》 https://blog.tensorflow.org/2020/05/bigtransfer-bit-state-of-art-transfer-learning-computer-vision.html
【强化学习算法体系】’RL Taxonomy - Loose taxonomy of reinforcement learning algorithms' https://github.com/bennylp/RL-Taxonomy
《Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning》 https://github.com/cvlab-stonybrook/Scanpath_Prediction
【强化学习文献调研】’rl-paper-study - Reinforcement Learning paper review study' https://github.com/utilForever/rl-paper-study
【强化学习研究相关资源与实现】 https://github.com/RL-Research-Cohiba/Reinforcement_Learning
【Coursera强化学习专项课程(University of Alberta)】 https://www.coursera.org/specializations/reinforcement-learning
【Kaggle新课：游戏AI入门与强化学习教程】 https://www.kaggle.com/learn/intro-to-game-ai-and-reinforcement-learning
【TorchRL：强化学习算法的PyTorch实现】’TorchRL - Pytorch Implementation of Reinforcement Learning Algorithms ( Soft Actor Critic(SAC)/ DDPG / TD3 /DQN / A2C/ PPO / TRPO)' https://github.com/RchalYang/torchrl
【DL_RL_Zoo：PyTorch深度强化学习算法库】’An lightweight, stable, efficient DRL PyTorch implement(DDPG, TD3, PPO, SAC, InterAC, InterSAC and DQN)’ https://github.com/Yonv1943/DL_RL_Zoo
【megastep：在单GPU上构建百万FPS强化学习环境】 https://github.com/andyljones/megastep
【用近似策略优化(PPO)玩超级马里奥(PyTorch)】 https://github.com/uvipen/Super-mario-bros-PPO-pytorch
'FQF, IQN and QR-DQN in PyTorch' https://github.com/ku2482/fqf-iqn-qrdqn.pytorch
"VariBAD: A very good method for Bayes-Adaptive Deep RL via Meta-Learning" https://github.com/lmzintgraf/varibad
Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning / ICLR 2020 https://github.com/pokaxpoka/netrand
Real-World Reinforcement Learning (RWRL) Challenge Framework https://github.com/google-research/realworldrl_suite
This is a framework for the research on multi-agent reinforcement learning and the implementation of the experiments in the paper titled by ''Shapley Q-value: A Local Reward Approach to Solve Global Reward Games''. https://github.com/hsvgbkhgbv/SQDDPG
Repository for Iterated Relearning: The Impact of Non-stationarity on Generalisation in Deep Reinforcement Learning https://github.com/maximilianigl/rl-iter
【强化学习实现集】’Basic RL Algorithms Implementations - RL implementations' https://github.com/Denys88/rl_games
An algorithm that generalizes the paradigm of self-play reinforcement learning and search to imperfect-information games. https://github.com/facebookresearch/rebel
https://github.com/Tencent/GameAISDK
GenRL：PyTorch强化学习库，重在可复现性、易用性和基准性 https://github.com/SforAiDl/genrl
machin：PyTorch强化学习库 https://github.com/iffiX/machin
基于MiniGrid的轻量多智能体gridworld Gym强化学习环境 https://github.com/ArnaudFickinger/gym-multigrid
李宏毅深度强化学习笔记(LeeDeepRL-Notes) https://datawhalechina.github.io/leedeeprl-notes/
DeepRL-TensorFlow2：TensorFlow2实现的多种深度强化学习算法 https://github.com/marload/DeepRL-TensorFlow2
DeepMind Lab2D：智能体AI研究2D模拟环境 https://github.com/deepmind/lab2d
深度强化学习算法的27个实例项目 https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms
离线强化学习：从算法设计到实际应用 https://nips.cc/Conferences/2020/Schedule?showEvent=16641 https://colab.research.google.com/drive/1oJOYlAIOl9d1JjlutPY66KmfPkwPCgEE?usp=sharing
David Silver的强化学习课程 https://www.bilibili.com/video/BV1Vp411d7vj/
《强化学习：原理与Python实现》随书源码 https://github.com/ZhiqingXiao/rl-book
RL environment list：强化学习开放环境大列表 https://github.com/clvrai/awesome-rl-envs
基于视觉模型强化学习中的设计权衡评价 https://github.com/google-research/world_models
Pytorch/Tensorflow 2实现的深度强化学习集算法锦 https://github.com/RITCHIEHuang/DeepRL_Algorithms
Sequoia - 面向持续学习、强化学习和自监督学习研究的实验库 https://github.com/lebrice/Sequoia
MTEnv：强化学习多任务环境 https://github.com/facebookresearch/mtenv
https://github.com/rlberry-py/rlberry
ReBeL：用单一AI算法玩所有游戏的新尝试，可以玩国际象棋、围棋、扑克、掷骰子等 https://ai.facebook.com/blog/rebel-a-general-game-playing-ai-bot-that-excels-at-poker-and-more/
离线强化学习算法大列表 https://github.com/hanjuku-kaso/awesome-offline-rl
MTRL：多任务强化学习算法库 https://github.com/facebookresearch/mtrl
深度强化学习相关笔记和PPT https://github.com/wangshusen/DRL
github.com/bentrevett/pytorch-rl
Crafter：强化学习开放世界生存(开发)环境 github.com/danijar/crafter
强化学习调试技巧与策略 https://andyljones.com/posts/rl-debugging.html
Benchmarks for Deep Off-Policy Evaluation：离线强化学习基准 github.com/google-research/deep_ope
github.com/freefuiiismyname/ddz-ai
用Deep Q-learning玩Chrome恐龙跳跳小游戏 github.com/uvipen/Chrome-dino-deep-Q-learning-pytorch
coax：基于OpenAI Gym和JAX的Python强化学习模块化框架 github.com/coax-dev/coax
PyTorch实现的强化学习算法集 github.com/gordicaleksa/pytorch-learn-reinforcement-learning
《MedSelect: Selective Labeling for Medical Image Classification Combining Meta-Learning with Deep Reinforcement Learning》(2021) github.com/stanfordmlgroup/MedSelect
MazeRL :面向应用的深度强化学习框架，用于解决现实世界中的决策问题 github.com/enlite-ai/maze
DouZero：用深度强化学习玩斗地主 github.com/kwai/DouZero
基于机器学习的游戏智能体快速训练 github.com/google-research/falken
ElegantRL：用PyTorch实现的轻量、高效、稳定的深度强化学习算法 github.com/AI4Finance-LLC/ElegantRL
DouZero_For_Happy_DouDiZhu: 将DouZero用于欢乐斗地主实战 - 基于DouZero定制AI实战欢乐斗地主 github.com/tianqiraf/DouZero_For_HappyDouDiZhu
YARR： PyTorch机器人/强化学习框架 github.com/stepjam/YARR
xagents：Tensorflow2可重用、可扩展、高性能强化学习算法迷你库 github.com/schissmantics/xagents
https://www.bilibili.com/video/BV1kQ4y1Y7Gn/
Yet Another Reinforcement Learning Tutorial：强化学习教程 github.com/sjchoi86/rl_tutorial
基于深度强化学习的原神自动钓鱼AI github.com/7eu7d7/genshin_auto_fish
RLkit：强化学习算法(PyTorch)实现集 github.com/rail-berkeley/rlkit
ElegantRL：用PyTorch实现的轻量、高效、稳定的深度强化学习算法 github.com/AI4Finance-LLC/ElegantRL
EasyRL - 强化学习中文教程,主要包含了强化学习概述、马尔可夫决策过程 、表格型方法、策略梯度、模仿学习等内容。 github.com/datawhalechina/easy-rl 模仿学习 vs. 离线强化学习 https://www.bilibili.com/video/BV1dU4y1f7t6/
A Survey of Explainable Reinforcement Learning https://arxiv.org/abs/2202.08434
免费书(含中文版)：深度强化学习——基础、研究与应用 https://deepreinforcementlearningbook.org/
Gym-μRTS (pronounced "gym-micro-RTS”)：基于实时策略游戏模拟器μRTS的强化学习环境 github.com/vwxyzjn/gym-microrts
Avalanche RL: 端到端持续强化学习库 github.com/ContinualAI/avalanche-rl
DeepForSpeed: Data Wanted：用卷积网络玩极品飞车游戏 github.com/edilgin/DeepForSpeed
GitHub 上的深度学习技术书籍：《蘑菇书 EasyRL》，覆盖了强化学习、马尔可夫决策过程、策略梯度、模仿学习等多个知识点。 GitHub：github.com/datawhalechina/easy-rl 该教程也称为 “蘑菇书”，寓意是希望此书能够为读者注入活力，让读者 “吃” 下这本蘑菇之后，能够饶有兴致地探索强化学习，像马里奥那样愈加强大，继而在人工智能领域觅得意外的收获。
TorchRL：PyTorch强化学习库 github.com/facebookresearch/rl
AI-Optimizer：下一代深度强化学习框架 github.com/TJU-DRL-LAB/AI-Optimizer
《动手学强化学习》随书代码 github.com/boyu-ai/Hands-on-RL
Hugging Face深度强化学习课程 github.com/huggingface/deep-rl-class
Super-Mario-RL：用深度强化学习玩超级玛丽 github.com/jiseongHAN/Super-Mario-RL
【Awesome-Implicit-NeRF-Robotics：与机器人/强化学习领域相关的隐表示与NeRF的论文资源大列表】’Awesome-Implicit-NeRF-Robotics - A comprehensive list of Implicit Representations and NeRF papers relating to Robotics/RL domain, including papers, codes, and related websites' by Zubair Irshad GitHub: github.com/zubair-irshad/Awesome-Implicit-NeRF-Robotics
【Honor of Kings Game Environment：支持强化学习研究的王者荣耀游戏环境，包括1v1游戏核心、强化学习框架和基于训练框架的PPO算法实现】’Honor of Kings Game Environment' by tencent-ailab GitHub: github.com/tencent-ailab/hok_env
复旦魏忠钰老师手把手教你学强化学习 https://space.bilibili.com/471559565/channel/seriesdetail?sid=2413153
'MO-Gym: Multi-Objective Reinforcement Learning Environments' by Lucas Alegre GitHub: github.com/LucasAlegre/mo-gym
'Scikit-decide for Python - AI framework for Reinforcement Learning, Automated Planning and Scheduling' by Airbus GitHub: github.com/airbus/scikit-decide
'RLcode - 白话强化学习‘ by louisnino GitHub: github.com/louisnino/RLcode
【强化学习手把手实战课程】《Reinforcement Learning Course: Hands-On, Step by Step, and Free》 https://datamachines.xyz/the-hands-on-reinforcement-learning-course-page/
【huggingface深度强化学习开放课程2.0】《Deep Reinforcement Learning Course》 simoninithomas.github.io/deep-rl-course/
'DI-1024：深度强化学习 + 1024游戏 人机协作共同解密 (Deep Reinforcement Learning + 1024 Game)' OpenDILab GitHub: github.com/opendilab/DI-1024
【强化学习实战教程】’The Hands-on Reinforcement Learning course - Free course that takes you from zero to Reinforcement Learning PRO' Pau Labarta Bajo GitHub: github.com/Paulescu/hands-on-rl
【人工反馈强化学习(RLHF)简要解析】“Reinforcement Learning from Human Feedback (RLHF) - a simplified explanation” gist.github.com/JoaoLages/c6f2dfd13d2484aa8bb0b2d567fbf093