tocom242242 / qmix_tf2

QMIX implemented in TensorFlow 2
16 stars 4 forks source link

Apply this codebase to Starcraft II environment #1

Open yunanyan opened 3 years ago

yunanyan commented 3 years ago

Hi,

If I want to apply this codebase to multiagent game environment such as Starcraft II. What part of the network should be changed?

Thank you!

tocom242242 commented 3 years ago

Thanks for your question!

To be honest, I haven't really thought about it. So I don't know exactly, but I think the major change of this code for starcraft2 are

  1. To use recurrent network for each agent network

  2. To change the memory which can handle time series data

Actually, I think you should to refer to the following QMIX implementation (implemented by the author of QMIX). https://github.com/oxwhirl/pymarl

I'm sorry I couldn't help you.

Regards