search

RLE-Foundation / RLeXplore

RLeXplore provides stable baselines of exploration methods in reinforcement learning, such as intrinsic curiosity module (ICM), random network distillation (RND) and rewarding impact-driven exploration (RIDE).
https://docs.rllte.dev/
MIT License
333 stars 16 forks source link

State of this project? #12

Open dominikonysz opened 4 months ago

dominikonysz commented 4 months ago

Hey,

I was just wondering what the state of this project is, since there has been new activity recently. I understand that it had been merged with RLLTE which rather seems to be a replacement for stable-baselines3 than an addition to it's ecosystem. My interest in particular is to combine MaskablePPO with ICM, which this project would have been ideal for since the other projects are missing one of the building blocks each, unfortunately.

So is there any interest in continuing the development of exploration add-ons for stable-baselines3?

yuanmingqi commented 4 months ago

Of course, we will publish a big update recently. You can check this branch https://github.com/RLE-Foundation/rllte/blob/reward/ for the lastest code and there is an example https://github.com/RLE-Foundation/rllte/blob/reward/experimental/rllte_to_sb3.py for using RLeXplore with SB3.

dominikonysz commented 4 months ago

Great, thank you!

Unfortunately I'm having some issues with installing it, but for that see https://github.com/RLE-Foundation/rllte/issues/44.