This repo contains only IPython code from “Hands-on-RL” with my own understanding. I highly recommend getting your hands dirty with the code. You will definitely learn more than you could imagine.
One recommended learning path is to follow: MDP → AC → TRPO → GRPO.
If you find this repo helpful, please give it a star. Thank you (I want the badge, btw 🥺).
If you have questions, suggestions, bug reports, or you want to discuss with me, please email:
ruochangli@gmail.com
If your issue does not receive a timely response, you are welcome to reach out via email.
This repo is built on https://github.com/boyu-ai/Hands-on-RL and https://docs.swanlab.cn/examples. I would like to thank the professors for providing the excellent codebase, which has been instrumental in advancing my research on reinforcement learning.