Graph Neural Networks for Decentralized Multi-Agent Perimeter Defense

TL;DR

This paper introduces a GNN-based imitation learning approach for decentralized multi-agent perimeter defense, enabling scalable and effective intruder capture strategies that generalize from small to large teams.

Contribution

The paper presents a novel GNN framework that learns decentralized defense strategies from a centralized expert, improving scalability and performance in large-scale scenarios.

Findings

GNN-based network outperforms baseline algorithms in capturing intruders.

The learned strategies generalize from small to large team sizes.

The approach effectively imitates centralized expert decisions in a decentralized setting.

Abstract

In this work, we study the problem of decentralized multi-agent perimeter defense that asks for computing actions for defenders with local perceptions and communications to maximize the capture of intruders. One major challenge for practical implementations is to make perimeter defense strategies scalable for large-scale problem instances. To this end, we leverage graph neural networks (GNNs) to develop an imitation learning framework that learns a mapping from defenders' local perceptions and their communication graph to their actions. The proposed GNN-based learning network is trained by imitating a centralized expert algorithm such that the learned actions are close to that generated by the expert algorithm. We demonstrate that our proposed network performs closer to the expert algorithm and is superior to other baseline algorithms by capturing more intruders. Our GNN-based network is trained at a small scale and can be generalized to large-scale cases. We run perimeter defense games in scenarios with different team sizes and configurations to demonstrate the performance of the learned network.