search

SforAiDl / genrl

A PyTorch reinforcement learning library for generalizable and reproducible algorithm implementations with an aim to improve accessibility in RL
https://genrl.readthedocs.io
MIT License
403 stars 59 forks source link

GymWrapper is not compatible for multiagent-particle-env #324

Closed AdityaKapoor74 closed 3 years ago

AdityaKapoor74 commented 4 years ago

I believe we will have to write a separate wrapper or incorporate it into the current one. I think the former approach is better as we can add other new features to it as well

Sharad24 commented 4 years ago

Should we even support Multiagent-particle-env? I dont think we should.

Or, did you mean any Multi Agent Env Wrapper here?

veds12 commented 4 years ago

Using Petting Zoo instead of multiagent-particle-env might be a better idea. The API is very similar to that of Gym

Sharad24 commented 4 years ago

Using Petting Zoo instead of multiagent-particle-env might be a better idea. The API is very similar to that of Gym

+1

sampreet-arthi commented 3 years ago

Can we close this and #325 as we're shifting to Petting Zoo? @AdityaKapoor74 @veds12

Sharad24 commented 3 years ago

Yes. Petting Zoo has suppose for particle envs too.