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

Typo in train.py #44

Open opt12 opened 4 years ago

opt12 commented 4 years ago

After walking through the code, I think, that there is a type here: https://github.com/openai/maddpg/blob/3ceefa0ada3ff31d633dd0bde8ff95213ce99be3/experiments/train.py#L141

Should be: agent_info[-1][i].append(info['n']) instead of `info_n['n']'.