MAGNet: Multi-agent Graph Network for Deep Multi-agent Reinforcement Learning
This work addresses the problem of improving coordination and performance in multi-agent reinforcement learning environments for AI agents.
This paper proposes MAGNet, a novel multi-agent reinforcement learning approach that uses a relevance graph from self-attention and a message-generation technique. It significantly outperforms state-of-the-art MARL solutions like MADQN, MADDPG, and QMIX in predator-prey and Pommerman environments.
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