Table of Contents
Cart Pole
Tutorials
Google Colaboratory - DQN/MLP
https://colab.research.google.com/drive/1goyULtqCz8FKjc7-RYww2Y2_B3OTs8f3
Google Colaboratory - Rainbow/MLP (RLlib)
https://colab.research.google.com/drive/1xuJyTHinhJABp9ct9tCy17GbnuP9JE1b
Google Colaboratory - PPO/MLP (Stable Baselines 3)
https://colab.research.google.com/drive/1s7ycZBPAojJqHOmZE0fq7PtMZOqUNot9
Trained Models
Results
DQN/MLP
Rainbow/MLP (RLlib) - to be tuned...
PPO/MLP (Stable Baselines 3)
Video
References
https://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html
https://www.gymlibrary.dev/
https://github.com/openai/gym/wiki/CartPole-v0
https://unproductive.dev/rl-implementation-dqn/
https://take-tech-engineer.com/dqn-atari-breakout-pytorch/
https://www.anarchive-beta.com/entry/2022/11/22/180000
https://stable-baselines3.readthedocs.io/
https://note.com/npaka/n/nc772d85dcae0
https://note.com/npaka/n/n5a778ce0bd35
https://note.com/npaka/n/na7a409cbadc7
https://qiita.com/sugulu_Ogawa_ISID/items/3c7d6cbe600d455e853b
https://docs.ray.io/en/latest/rllib/
https://qiita.com/rui0930/items/b21772b8a01fcf73ac36
https://www.slideshare.net/juneokumura/dqnrainbow
https://horomary.hatenablog.com/entry/2021/02/11/173638
https://dmv.nico/ja/articles/how_to_use_rllib/