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
@article{arxiv.2012.09762,
title = {MAGNet: Multi-agent Graph Network for Deep Multi-agent Reinforcement Learning},
author = {Aleksandra Malysheva and Daniel Kudenko and Aleksei Shpilman},
journal= {arXiv preprint arXiv:2012.09762},
year = {2020}
}
Comments
arXiv admin note: substantial text overlap with arXiv:1811.12557