@inproceedings{1095262df0dd477d9e3e9fd470f2392b,
title = "Deep coordination graphs",
abstract = "This paper introduces the deep coordination graph (DCG) for collaborative multi-agent reinforcement learning. DCG strikes a flexible tradeoff between representational capacity and generalization by factoring the joint value function of all agents according to a coordination graph into payoffs between pairs of agents. The value can be maximized by local message passing along the graph, which allows training of the value function end-to-end with Q-learning. Payoff functions are approximated with deep neural networks that employ parameter sharing and low-rank approximations to significantly improve sample efficiency. We show that DCG can solve predatorprey tasks that highlight the relative overgeneralization pathology, as well as challenging StarCraft II micromanagement tasks.",
author = "Wendelin B{\"o}hmer and Vitaly Kurin and Shimon Whiteson",
year = "2020",
language = "English",
series = "37th International Conference on Machine Learning, ICML 2020",
publisher = "International Machine Learning Society (IMLS)",
pages = "957--968",
editor = "Hal Daume and Aarti Singh",
booktitle = "37th International Conference on Machine Learning, ICML 2020",
note = "37th International Conference on Machine Learning, ICML 2020 ; Conference date: 12-07-2020 Through 18-07-2020",
}