MARL algorithm

[wanghui589]

demo_ Maddpg does not work. Can someone give a demoof multi-agent algorithm implementation? Such as mappo Thank you very much.

[leilei-0428]

你的mappo可以正常运行吗？ActorMAPPO, CriticMAPPO是在哪里找到的呢？

[josyulakrishna]

Any updates on this, how do i define the env variables etc? an example is very much appreciated, thank you.

[shixun404]

Any updates on this, how do i define the env variables etc? an example is very much appreciated, thank you.

@josyulakrishna Hi! I can provide a QMIX single file version as soon as possible.

[josyulakrishna]

@shixun404 that'd be immensely helpful, for our project we want MAPPO or QMIX whichever is available, can you send that. Thank you!

edit: college project

[shixun404]

@josyulakrishna Hi, there is an available demo for QMIX in a past version of ElegantRL, https://github.com/AI4Finance-Foundation/ElegantRL/commit/02dd28aa25fce9db2a663dfa5d3052551bd83561.

• You can checkout the version by running the following command

git checkout 02dd28

• This demo tests QMIX algorithm on SMAC tasks. You can install SMAC by following the instructions in https://github.com/AI4Finance-Foundation/ElegantRL/blob/02dd28aa25fce9db2a663dfa5d3052551bd83561/elegantrl/envs/starcraft/README.md
• Run the following command to test QMIX

python3 elegantrl/Demo_SMAC.py --config=qmix --env-config=sc2 with env_args.map_name=corridor