ModGNN: Expert Policy Approximation in Multi-Agent Systems with a Modular Graph Neural Network Architecture
This work addresses the need for better coordination strategies in multi-agent systems, but it is incremental as it builds upon existing GNN approaches.
The paper tackled the problem of improving performance and generalization in multi-agent systems by introducing ModGNN, a decentralized framework that generalizes Graph Convolutional Networks (GCNs), and demonstrated its effectiveness in the multi-agent flocking problem with improved generalization to new environments.
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.