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 architecture #77

Closed Boxxfish closed 8 months ago

Boxxfish commented 8 months ago

Adds a deepset_block architecture for permutation invariant processing, and applies it to the model when --preprocess is passed to the training script.