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
MIT License
1.66k stars 494 forks source link

The code does not converged #34

Open sjq19960802 opened 5 years ago

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.

CoulsonZhao commented 3 years ago

It seems the loss didn't backward?