From fd9ffc9eaab6d9a77869768d75819cf7aa4d3c69 Mon Sep 17 00:00:00 2001
From: Hari <harisankar995@gmail.com>
Date: Fri, 29 Dec 2023 17:08:30 +0100
Subject: [PATCH] updated references

---
 README.md             | 17 ++++++++++++++++-
 docs/INTRO.md         |  2 +-
 examples/train_ppo.py |  2 +-
 3 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 5cb030f..b4217f6 100644
--- a/README.md
+++ b/README.md
@@ -5,7 +5,7 @@
 [![Pipeline](https://github.com/harisankar95/voxelgym2D/actions/workflows/test-main.yml/badge.svg?branch=main)](https://github.com/harisankar95/voxelgym2D/actions/workflows/test-main.yml)
 [![codestyle](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
-A gym environment for voxel/grid based reinforcement learning for path planning.
+A gymnasium environment for voxel/grid based reinforcement learning for path planning.
 
 <div id="solution-table">
     <table>
@@ -109,7 +109,22 @@ The documentation can be found [here](https://harisankar95.github.io/voxelgym2D/
 
 Contributions are welcome! Please open an issue or a pull request.
 
+## Citation
+
+If you use this project in your research, please cite it using the following BibTeX entry:
+
+```bibtex
+@misc{Babu_2023,
+author={Babu, Harisankar}, 
+title={Reinforcement Learning Based Path Planning for Autonomous Flight},
+url={https://publica.fraunhofer.de/handle/publica/442672},
+year={2023}, 
+month={Jan},
+}
+```
+
 ## References
 
+- [Gymnasium](https://gymnasium.farama.org/)
 - [OpenAI Gym](https://arxiv.org/abs/1606.01540)
 - [Stable Baselines 3](http://jmlr.org/papers/v22/20-1364.html)
diff --git a/docs/INTRO.md b/docs/INTRO.md
index a1bc086..c3b68fb 100644
--- a/docs/INTRO.md
+++ b/docs/INTRO.md
@@ -1,6 +1,6 @@
 # Voxelgym2D
 
-A gym environment for voxel/grid based reinforcement learning for path planning.
+A gymnasium environment for voxel/grid based reinforcement learning for path planning.
 
 <div id="solution-table">
     <table>
diff --git a/examples/train_ppo.py b/examples/train_ppo.py
index a82bde1..b144571 100644
--- a/examples/train_ppo.py
+++ b/examples/train_ppo.py
@@ -150,7 +150,7 @@ def func(progress_remaining: float) -> float:
         normalize_images=True,
         features_extractor_class=SimpleCNN,
         features_extractor_kwargs=dict(features_dim=2048),
-        net_arch=[dict(vf=[512, 256], pi=[512, 256])],
+        net_arch=dict(vf=[512, 256], pi=[512, 256]),
     )
 
     model = PPO(