Issue with MADDPG and MATD3

[Gabr1e1]

Hi! I am trying to use ElegantRL for multi-agent RL training as it seems very well written.

I tried to use MADDPG or MATD3. But none of these agents seem to be runnable. For example, the construction method for AgentDDPG requires arguments: https://github.com/AI4Finance-Foundation/ElegantRL/blob/b447f3a04993e0ab8fc11017c1b20c6d560f493b/elegantrl/agents/AgentDDPG.py#L29

But the MADDPG or MATD3 implementation doesn't provide that. https://github.com/AI4Finance-Foundation/ElegantRL/blob/b447f3a04993e0ab8fc11017c1b20c6d560f493b/elegantrl/agents/AgentMADDPG.py#L43

There are also other places that don't seem to be compatible.

I wonder if this is a problem with the multi-agent implementations using a legacy version of the codebase. And is it possible to provide a minimal working demo for MADDPG or MATD3?

Thanks a lot!!

[shixun404]

@Gabr1e1 Hi, this is a MADDPG demo https://github.com/shixun404/MADDPG_Demo. Thanks for your interest in ElegantRL.

[Gabr1e1]

Thank you for your response!

This repo (https://github.com/shixun404/MADDPG_Demo) still contains the same bugs:

https://github.com/shixun404/MADDPG_Demo/blob/54a0f1d8d86b9baa37217c345e942a1cb2c73966/agent.py#L274

Can you confirm that the demo is runnable?