Table of Contents

Sea Lane

Tutorials

Google Colaboratory - DQN/MLP (Stable Baselines 3)
https://colab.research.google.com/drive/1hBgYbzpZr5TAyaXmBocxZXdYmQ9zBh26

Google Colaboratory - PPO/MLP (Stable Baselines 3)
https://colab.research.google.com/drive/1KhqJ4mtMD0oL16Us45JX3i-d-mkBWJRj

Google Colaboratory - Recurrent PPO/MLP (Stable Baselines 3 - Contrib)
https://colab.research.google.com/drive/13PNP10S-7HaKwDhC4g886jizpL4-ZTsR

Google Colaboratory - ARS/MLP (Stable Baselines 3 - Contrib)
https://colab.research.google.com/drive/16BjGBIEkTd3yM_8kVU1j403PDDpCfWG3

Results

DQN/MLP (Stable Baselines 3) - to be trained...

PPO/MLP (Stable Baselines 3) - to be tuned...

Recurrent PPO/MLP (Stable Baselines 3 - Contrib) - to be tuned...

ARS/MLP (Stable Baselines 3 - Contrib) - to be tuned...

Video

References

https://stable-baselines3.readthedocs.io/
https://sb3-contrib.readthedocs.io/
https://stable-baselines.readthedocs.io/en/master/guide/rl_tips.html
https://note.com/npaka/n/nc90b305f4ca0
https://frame-illust.com/fi/wp-content/uploads/2017/06/map-kanto.png