-
Notifications
You must be signed in to change notification settings - Fork 837
Support Pettingzoo Multi-agent Atari envs with PPO #188
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.
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
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
@benblack769 @araffin @Miffyli @jkterry1 @kcorder would you mind helping review this PR? In particular, could you help review the following:
Thanks! |
This all looks good to me! Just some things I think we should try out:
|
Thank you @kcorder, I’d be happy to try out the no-op reset wrapper. Is the InvertColor agent indicator in supersuit? Also see https://wandb.ai/costa-huang/cleanRL/reports/MA-ALE--VmlldzoxNzAzMDQx#invert-color-indicator which shows the performance of the invertcolor indicator - at least in pong it does not perform as well as the naive indicator. |
Oh interesting, good to know about agent indicator - I hadn't tried myself. The NoopReset is here: https://github.com/jkterry1/MA-ALE2/blob/74f562d088c795e7fa4fdeba494f2573ac9c6c7e/env_utils.py#L324-L345 We've been using this InvertColorAgentIndicator - there was a bug fix there since the original code actually |
@kcorder thanks for the helpful pointers. While it would be interesting to try this preprocessing, I would like to defer this as future work since we are aiming for a 1.0.0 release soon. |
Description
Follow up to #144.
Types of changes
Checklist:
pre-commit run --all-files
passes (required).mkdocs serve
.If you are adding new algorithms or your change could result in performance difference, you may need to (re-)run tracked experiments. See #137 as an example PR.
--capture-video
flag toggled on (required).mkdocs serve
.width=500
andheight=300
).