We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. We demonstrate that decentralized, population-based training with co-play can lead to a progression in agents' behaviors: from random, to simple ball chasing, and finally showing evidence of cooperation. Our study highlights several of the challenges encountered in large scale multi-agent training in continuous control. In particular, we demonstrate that the automatic optimization of simple shaping rewards, not themselves conducive to co-operative behavior, can lead to long-horizon team behavior. We further apply an evaluation scheme, grounded by game theoretic principals, that can assess agent performance in the absence of pre-defined evaluation tasks or human baselines.
@article{arxiv.1902.07151,
title = {Emergent Coordination Through Competition},
author = {Siqi Liu and Guy Lever and Josh Merel and Saran Tunyasuvunakool and Nicolas Heess and Thore Graepel},
journal= {arXiv preprint arXiv:1902.07151},
year = {2021}
}