ATOC

Multi-Actor-Attention-Critic

Code for Learning Attentional Communication for Multi-Agent Cooperation (Jiechuan Jiang, Zongqing Lu, NIPS 2018)

Requirements

• Python 3.6.8
• My fork of Multi-agent Particle Environments
• PyTorch, version: 1.6.0
• OpenAI Gym, version: 0.9.4

The versions are just what I used and not necessarily strict requirements.

How to Run

All training code is contained within train.py. To view options simply run:

python train.py --help

It is not the official source code, and it has not been tested yet. I need some help to improve it.