Learning to Coordinate via Multiple Graph Neural Networks

TL;DR

This paper introduces MGAN, a novel multi-agent reinforcement learning algorithm that leverages multiple graph neural networks to improve agent collaboration, interpretability, and credit assignment.

Contribution

It proposes a new approach combining graph convolutional networks with value-decomposition for enhanced multi-agent coordination.

Findings

Effective agent representation learning demonstrated

Improved interpretability of agent actions

Enhanced coordination performance

Abstract

The collaboration between agents has gradually become an important topic in multi-agent systems. The key is how to efficiently solve the credit assignment problems. This paper introduces MGAN for collaborative multi-agent reinforcement learning, a new algorithm that combines graph convolutional networks and value-decomposition methods. MGAN learns the representation of agents from different perspectives through multiple graph networks, and realizes the proper allocation of attention between all agents. We show the amazing ability of the graph network in representation learning by visualizing the output of the graph network, and therefore improve interpretability for the actions of each agent in the multi-agent system.