Decentralized multi-agent pursuit using Deep Reinforcement Learning

Cristino De Souza, Rhys Newbury, Akansel Cosgun, Pedro Castillo, Boris Vidolov, Dana Kulic

Research output: Contribution to journalArticleResearchpeer-review

3 Citations (Scopus)


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 non-holonomic 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.

Original languageEnglish
Pages (from-to)4552-4559
Number of pages8
JournalIEEE Robotics and Automation Letters
Issue number3
Publication statusPublished - Jul 2021


  • cooperating robots
  • Multi-robot systems
  • reinforcement learning

Cite this