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

Inner-Outer Loop #13

Open

YanickZengaffinen opened this issue May 15, 2024 · 0 comments

Labels

on hold

Milestone

Poster Presentation

Collaborator

YanickZengaffinen commented May 15, 2024 •

edited

Loading

We should have a clean impl of inner-outer-loop that works with all our new code

create new file with train_inner_outer_MAL, analogously to how we did for contextualized in train.py/train_ppo.py
do inner-outer-loop: for one step in model, do many steps on policy (so it's best-response)

Ideally, the follower learning algorithm can later be replaced easily. E.g. with meta-learners

YanickZengaffinen added this to the Poster Presentation milestone

YanickZengaffinen assigned Angramme

YanickZengaffinen added the on hold label

YanickZengaffinen unassigned Angramme

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