Does macad-gym support multi-agent algos training?

[dineshresearch]

will this currently support multi agent RL(MARL) algos like https://github.com/decisionforce/CoPO

I am particularly interested in the Multi-vehicle cooperation and competition at intersection case?

any help would be highly appreciated

[praveen-palanisamy]

Hi @dineshresearch ,
Yes, you can use a multi-agent RL algorithm like the Coordinated Policy Optimization (CoPO). Please see the MACAD-Agents repository for multi-agent training code examples.

[praveen-palanisamy]

Converting this question to a GitHub discussion. Please mark the discussion as answered if you got the answer to your question.

[6Lackiu]

will this currently support multi agent RL(MARL) algos like https://github.com/decisionforce/CoPO

I am particularly interested in the Multi-vehicle cooperation and competition at intersection case?

any help would be highly appreciated

@dineshresearch Hi, have you successfully run CoPO in macad-gym?