DLR-RM / stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
https://stable-baselines3.readthedocs.io
MIT License
8.35k stars 1.6k forks source link

[Feature Request] Random Network Distillation with PPO (RND-PPO) #1935

Closed edofazza closed 1 week ago

edofazza commented 1 month ago

🚀 Feature

It would be interesting to integrate Random Network Distillation policies (https://arxiv.org/abs/1810.12894) to be used with PPO.

Motivation

RND implementation on GitHub are scarse and many of them are very old and not practical to use. Having this features inside stable-baseline3 could improve researches in many field.

Pitch

No response

Alternatives

No response

Additional context

No response

Checklist

araffin commented 1 month ago

Hello, if you want SB3 + RND, you should probably have a look at https://github.com/RLE-Foundation/RLeXplore (the link is in our doc).