RL: thoughts, content for self-teaching and more

Proximal Policy Optimization (PPO)

Slides

PPO

Video

https://www.youtube.com/watch?v=uRNL93jV2HE

Labs

https://master-dac.isir.upmc.fr/rld/rl/07-1-ppo_penalty.student.ipynb

https://master-dac.isir.upmc.fr/rld/rl/07-2-ppo_clip.student.ipynb

Additional material

All the versions of PPO in a fantastic blog

A fine-grained study about the factors behind PPO’s performance

The spinning up documentation

Sylvain Lamprier’s lesson

John Schulman’s slides