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.

翻译：近期在多智能体领域的研究展示了图神经网络（GNN）在学习复杂协调策略方面的潜力。然而，当前大多数方法采用图卷积网络（GCN）的微小变体，即对多智能体系统形成的通信图进行卷积操作。本文探究能否改进GCN的性能与泛化能力。我们提出ModGNN——一种去中心化框架，作为GCN的泛化形式，提供更高灵活性。为验证假设，我们在多智能体集群问题中评估ModGNN实现与多个基线方法的对比。消融分析表明，框架中最关键的组件是GCN中不存在的部分。通过改变智能体数量，我们还证明了一种与具体应用无关的ModGNN实现具有更强的环境泛化能力。