Replicable-MARL / MARLlib

One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)
https://marllib.readthedocs.io
MIT License
949 stars 154 forks source link

Great work! Is this compatible with latest RLLib? #80

Closed pengzhenghao closed 1 year ago

pengzhenghao commented 1 year ago

Great job! I like this comprehensive benchmark

I just developed CoPO, a MARL algorithm explicitly modeling the coordination between self-interested agents, based on latest RLLib ray=2.2.0. If this repo is compatible I would like to contribute my code to enrich this project.

Theohhhu commented 1 year ago

It is not. MARLlib is based on ray=1.8.0. No forward and backward compatibility