search

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
1.59k stars 484 forks source link

Update train.py #62

Closed duanzy18 closed 3 years ago

duanzy18 commented 3 years ago

The '-' in arguments' names in ./experiments/train.py should be changed to '_', or these arguments can not work (different from code below).

duanzy18 commented 3 years ago

Sorry.