Decentralized Multi-Agent Pursuit Using Deep Reinforcement Learning - Archive ouverte HAL Access content directly
Journal Articles IEEE Robotics and Automation Letters Year : 2021

Decentralized Multi-Agent Pursuit Using Deep Reinforcement Learning


Pursuit-evasion is the problem of capturing mobile targets with one or more pursuers. We use deep reinforcement learning for pursuing an omnidirectional 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, executed independently by each agent at run-time. The training uses curriculum learning, a sweeping-angle ordering to locally represent neighboring agents, and a reward structure that encourages a good formation and combines individual and group rewards. Simulated experiments with a reactive evader and up to eight pursuers show that our learning-based approach outperforms recent reinforcement learning techniques as well as nonholonomic adaptations of classical algorithms. The learned policy is successfully transferred to the real-world in a proof-of-concept demonstration with three motion-constrained pursuer drones.
Fichier principal
Vignette du fichier
RAL_hunterdrones_machinelearning.pdf (2.17 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03842721 , version 1 (22-11-2022)



Cristino de Souza, Rhys Newbury, Akansel Cosgun, Pedro Castillo Garcia, Boris Vidolov, et al.. Decentralized Multi-Agent Pursuit Using Deep Reinforcement Learning. IEEE Robotics and Automation Letters, 2021, 6 (3), pp.4552-4559. ⟨10.1109/LRA.2021.3068952⟩. ⟨hal-03842721⟩
21 View
4 Download



Gmail Facebook Twitter LinkedIn More