Stable-Baselines-Team
[Feature Request] BBF algorithm implementation
🚀 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
- [X] I have checked that there is no similar issue in the repo
- [X] If I'm requesting a new feature, I have proposed alternatives
Hello, That would indeed be a good addition for SB3 contrib, would you be willing to contribute?
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