MAGNet: Multi-Agent Graph Network for Deep Multi-Agent Reinforcement Learning

P. 171–176.

Shpilman A., Malysheva A., Kudenko D.

Over recent years, deep reinforcement learning has shown strong successes in complex single-Agent tasks, and more recently this approach has also been applied to multi-Agent domains. In this paper, we propose a novel approach, called MAGNet, to multi-Agent reinforcement learning that utilizes a relevance graph representation of the environment obtained by a self-Attention mechanism, and a message-generation technique. We applied our MAGnet approach to the synthetic predator-prey multi-Agent environment and the Pommerman game and the results show that it significantly outperforms state-of-the-art MARL solutions, including Multi-Agent Deep Q-Networks (MADQN), Multi-Agent Deep Deterministic Policy Gradient (MADDPG), and QMIX.

Keywords: машинное обучение, machine learning, Deep Reinforcement Learning, глубокое обучение с подкреплением

In book

Proceedings of 2019 XVI International Symposium "Problems of Redundancy in Information and Control Systems" (REDUNDANCY)

IEEE, 2019.