Skip to content
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

[Feature Request] BBF algorithm implementation #206

Open
2 tasks done
Alian3785 opened this issue Aug 26, 2023 · 2 comments
Open
2 tasks done

[Feature Request] BBF algorithm implementation #206

Alian3785 opened this issue Aug 26, 2023 · 2 comments
Labels
enhancement New feature or request

Comments

@Alian3785
Copy link

🚀 Feature

Can a recent BBF algorithm be added to the library- https://github.com/google-research/google-research/tree/master/bigger_better_faster?

Motivation

It is model free single agent RL algorithm which this library specializes in. It`s more sample-efficient then Dreamerv3 or PPO at least in some task

Pitch

Addition of BBF algorithm to the library so everyone can use it for custom environments

Alternatives

Add other algorithm with comparable efficiency

Additional context

paper - https://paperswithcode.com/paper/bigger-better-faster-human-level-atari-with

Checklist

  • I have checked that there is no similar issue in the repo
  • If I'm requesting a new feature, I have proposed alternatives
@Alian3785 Alian3785 added the enhancement New feature or request label Aug 26, 2023
@Alian3785 Alian3785 changed the title [Feature Request] request title [Feature Request] BBF algorithm implementation Aug 26, 2023
@araffin
Copy link
Member

araffin commented Aug 28, 2023

Hello,
That would indeed be a good addition for SB3 contrib, would you be willing to contribute?

@Alian3785
Copy link
Author

I have a knowledge of RL on the level of running stable baselines 3 on custom envs. So I`m willing but not able to do it.

Can contribute only by testing for now

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants