Explain PPO with RLlib - Githubissues

rlturkiye / flying-cavalry

Flying Cavalry Project - Ucan Kavalye Projesi

https://rlturkiye.com

MIT License

15 stars 1 forks source link

Explain PPO with RLlib #52

Open ugurkanates opened 3 years ago

ytaskiran commented 3 years ago

Fundamentals of PPO algorithm is presented.
Main rllib script and code design is introduced. (https://github.com/rlturkiye/flying-cavalry/tree/RLLIB/rllib)

Presentation Resources:

https://www.youtube.com/watch?v=5P7I-xPq8u8 https://www.youtube.com/watch?v=vQ_ifavFBkI https://www.youtube.com/watch?v=wM-Sh-0GbR4 https://towardsdatascience.com/on-policy-v-s-off-policy-learning-75089916bc2f https://openai.com/blog/openai-baselines-ppo/ https://jonathan-hui.medium.com/rl-proximal-policy-optimization-ppo-explained-77f014ec3f12 https://arxiv.org/pdf/1707.06347.pdf