openai / maddpg

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

https://arxiv.org/pdf/1706.02275.pdf

The code does not converged

sjq19960802 opened this issue 5 years ago · comments

sjq19960802 commented 5 years ago

I run the environment simple_spread_listener with the code and it does not converged. I haven't changed any code.

Pengbo Zhao commented 3 years ago

It seems the loss didn't backward?