Implementations about other compared algos.

ZhengYinan-AIR / OMIGA

[NeurIPS 2023] The official implementation of "Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization"

27 stars 3 forks source link

Implementations about other compared algos. #2

Closed RZ-Q closed 5 months ago

RZ-Q commented 5 months ago

Hi! In your paper, you compared OMIGA with BCQ-MA, CQL-MA, ICQ and OMAR. I have found the official implementations for ICQ-MA and OMAR, can you share your version for BCQ-MA and CQL-MA or just share the implementations link? This will help me a lot! Thanks for your work!

ZhengYinan-AIR commented 5 months ago

We modified the code based on bcq and cql into a multi-agent version. You can view the official code of these two algorithms.