search

starry-sky6688 / MADDPG

Pytorch implementation of the MARL algorithm, MADDPG, which correspondings to the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments".
537 stars 83 forks source link

关于参数共享机制的使用 #34

Closed wagh311 closed 1 year ago

wagh311 commented 1 year ago

大佬你好，我想请问一下，如果想将参数共享机制运用到MADDPG中，那么是只需要创建一个Actor网络和一个Critic网络呢？还是应该创建一个Actor网络和n个Critic网络呢（n为智能体数量）？

starry-sky6688 commented 1 year ago

一个Actor网络和一个Critic网络就可以了

wagh311 commented 1 year ago

谢谢！