reward is too large - Githubissues

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

1.65k stars 491 forks source link

Open Sherry-97 opened 4 years ago

Sherry-97 commented 4 years ago

When I ran python train.py --scenario simple, the reward function was too large, but I didn't change the code.

sunhuichao commented 2 weeks ago

Hi， Can you solve this problem? Thanks