Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learning

TL;DR

This paper introduces a novel framework using graph neural networks and imitation learning to synthesize scalable, decentralized controllers for multi-agent systems, addressing limitations of centralized approaches.

Contribution

The paper proposes a new GNN-based method for learning decentralized controllers that scale and transfer better than existing techniques.

Findings

GNNs successfully learn decentralized controllers for multi-agent tasks.

The approach scales to larger teams and transfers to unseen scenarios.

Effective in tasks like flocking and multi-agent path planning.

Abstract

Dynamical systems consisting of a set of autonomous agents face the challenge of having to accomplish a global task, relying only on local information. While centralized controllers are readily available, they face limitations in terms of scalability and implementation, as they do not respect the distributed information structure imposed by the network system of agents. Given the difficulties in finding optimal decentralized controllers, we propose a novel framework using graph neural networks (GNNs) to \emph{learn} these controllers. GNNs are well-suited for the task since they are naturally distributed architectures and exhibit good scalability and transferability properties. We show that GNNs learn appropriate decentralized controllers by means of imitation learning, leverage their permutation invariance properties to successfully scale to larger teams and transfer to unseen scenarios at deployment time. The problems of flocking and multi-agent path planning are explored to illustrate the potential of GNNs in learning decentralized controllers.