Giters

praveen-palanisamy / macad-gym

Multi-Agent Connected Autonomous Driving (MACAD) Gym environments for Deep RL. Code for the paper presented in the Machine Learning for Autonomous Driving Workshop at NeurIPS 2019:

Home Page:https://arxiv.org/abs/1911.04175

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Does macad-gym support multi-agent algos training?

dineshresearch opened this issue · comments

commented

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

commented

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.

commented

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