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

TL;DR

MAGNet introduces a relevance graph-based multi-agent reinforcement learning framework using self-attention and message generation, significantly outperforming existing methods in complex multi-agent environments.

Contribution

The paper presents MAGNet, a novel multi-agent reinforcement learning approach that leverages graph representations and self-attention for improved coordination.

Findings

MAGNet outperforms MADQN, MADDPG, and QMIX in synthetic and game environments.

The relevance graph and message-generation techniques enhance multi-agent cooperation.

Results demonstrate superior learning efficiency and policy quality.

Abstract

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