Towards Scalable Imitation Learning for Multi-Agent Systems with Graph Neural Networks

Siyu Zhou, Chaitanya Rajasekhar, Mariano J. Phielipp, Heni Ben Amor

TL;DR: Improve the scalability of graph neural networks on imitation learning and prediction of swarm motion

Abstract: We propose an implementation of GNN that predicts and imitates the motion be- haviors from observed swarm trajectory data. The network’s ability to capture interaction dynamics in swarms is demonstrated through transfer learning. We finally discuss the inherent availability and challenges in the scalability of GNN, and proposed a method to improve it with layer-wise tuning and mixing of data enabled by padding.

Keywords: Graph Neural Networks, Scalability, Swarms, Imitation