ModGNN: Expert Policy Approximation in Multi-Agent Systems with a Modular Graph Neural Network Architecture

TL;DR

ModGNN is a flexible, decentralized graph neural network architecture that enhances multi-agent coordination and generalization capabilities beyond traditional GCNs, demonstrated through flocking problem experiments.

Contribution

We propose ModGNN, a novel modular GNN framework that generalizes GCNs, improving performance and adaptability in multi-agent systems.

Findings

ModGNN outperforms baseline GCNs in multi-agent flocking tasks.

Ablation analysis identifies a key component absent in GCNs as crucial.

ModGNN generalizes better to different numbers of agents and environments.

Abstract

Recent work in the multi-agent domain has shown the promise of Graph Neural Networks (GNNs) to learn complex coordination strategies. However, most current approaches use minor variants of a Graph Convolutional Network (GCN), which applies a convolution to the communication graph formed by the multi-agent system. In this paper, we investigate whether the performance and generalization of GCNs can be improved upon. We introduce ModGNN, a decentralized framework which serves as a generalization of GCNs, providing more flexibility. To test our hypothesis, we evaluate an implementation of ModGNN against several baselines in the multi-agent flocking problem. We perform an ablation analysis to show that the most important component of our framework is one that does not exist in a GCN. By varying the number of agents, we also demonstrate that an application-agnostic implementation of ModGNN possesses an improved ability to generalize to new environments.