New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Compare PPO implementation to stable baselines #6

Open

AndreWeiner opened this issue Jan 31, 2023 · 0 comments

Collaborator

AndreWeiner commented Jan 31, 2023

Make a detailed comparison to the PPO implementation in stable baselines.

what is the influence of batch training?
are the stopping criteria identical (clipping, KL-divergence, MSE loss of value network)?
is the training order important (value vs. policy net)?
is it better to update both networks in the same loop?
is it possible to use generalized state-dependent exploration?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment