Pursuit-evasion is the problem of capturing mobile targets with one or more pursuers. We use deep reinforcement learning for pursuing an omni-directional target with multiple, homogeneous agents that are subject to unicycle kinematic constraints. We use shared experience to train a policy for a given number of pursuers that is executed independently by each agent at run-time. The training benefits from curriculum learning, a sweeping-angle ordering to locally represent neighboring agents and encouraging good formations with reward structure that combines individual and group rewards. Simulated experiments with a reactive evader and up to eight pursuers show that our learning-based approach, with non-holonomic agents, performs on par with classical algorithms with omni-directional agents, and outperforms their non-holonomic adaptations. The learned policy is successfully transferred to the real world in a proof-of-concept demonstration with three motion-constrained pursuer drones.
@article{arxiv.2010.08193,
title = {Decentralized Multi-Agent Pursuit using Deep Reinforcement Learning},
author = {Cristino de Souza and Rhys Newbury and Akansel Cosgun and Pedro Castillo and Boris Vidolov and Dana Kulic},
journal= {arXiv preprint arXiv:2010.08193},
year = {2021}
}