-
Notifications
You must be signed in to change notification settings - Fork 739
Remove SB3 as a necessary module #505
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
base: master
Are you sure you want to change the base?
Remove SB3 as a necessary module #505
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🚀 LGTM! Just make sure to update the documentation.
@@ -204,23 +129,27 @@ class BaseBuffer(ABC): | |||
:param n_envs: Number of parallel environments | |||
""" | |||
|
|||
observation_space: spaces.Space |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think the buffer classes are missing credits to SB3...
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Apologies, yes, I will add them
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the PR. It makes sense to me. Can you run an end-to-end PPO_atari training? If it looks reasonable feel free to merge.
Description
SB3 is used for the atari wrappers and buffers. However, this external module makes it more difficult for users to understand implementations (IMHO).
Further, for #502 it is limited by needing SB3 to update to support Gymnasium v1.1, for which this PR removes that problem
Finally, IMO the
ReplayBuffer
implementation in particular are inefficient, and could be improved which would be easier once incorporated into this repoTypes of changes
Checklist:
pre-commit run --all-files
passes (required).mkdocs serve
.If you need to run benchmark experiments for a performance-impacting changes:
--capture_video
.python -m openrlbenchmark.rlops
.python -m openrlbenchmark.rlops
utility to the documentation.python -m openrlbenchmark.rlops ....your_args... --report
, to the documentation.