Cumulative rewards are not promoted when use MADDPG

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

1.6k stars 484 forks source link

Cumulative rewards are not promoted when use MADDPG #26

Open jhcknzzm opened 5 years ago

jhcknzzm commented 5 years ago

When I used 4 agents of MADDPG to solve my own problems, the cumulative rewards I got did not improve. Sometimes the rewards gradually decreased. What is the reason?