EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi‐Agent Reinforcement Learning for Joint Police Patrol and Dispatch

Matthew Repasky, He Wang, Yao Xie

Naval Research Logistics (NRL) · 27.02.2026

DOI: 10.1002/nav.70059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Naval Research Logistics (NRL), online erschienen am 27.02.2026. Verfasst von Matthew Repasky und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation of Sri Lanka.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Police patrol units need to split their time between performing preventive patrol and being dispatched to serve emergency incidents. In the existing literature, patrol and dispatch decisions are often studied separately. We consider joint optimization of these two decisions to improve police operations efficiency and reduce response time to emergency calls. We propose a novel method for jointly optimizing multi‐agent patrol and dispatch to learn policies yielding rapid response times. Our method treats each patroller as an independent ‐learner (agent) with a shared deep ‐network that represents the state‐action values. The dispatching decisions are chosen using mixed‐integer programming and value function approximation from combinatorial action spaces. We demonstrate that this heterogeneous multi‐agent reinforcement learning approach is capable of learning joint policies that outperform those optimized for patrol or dispatch alone. Policies jointly optimized for patrol and dispatch can lead to more effective service while targeting demonstrably flexible objectives, such as those encouraging efficiency and equity in response.

Förderung

  • National Science Foundation of Sri Lanka

Zitieren

APA

Repasky, M., Wang, H., & Xie, Y. (2026). Multi‐Agent Reinforcement Learning for Joint Police Patrol and Dispatch. Naval Research Logistics (NRL). https://doi.org/10.1002/nav.70059

Vancouver

Repasky M, Wang H, Xie Y. Multi‐Agent Reinforcement Learning for Joint Police Patrol and Dispatch. Naval Research Logistics (NRL). 2026. doi:10.1002/nav.70059

BibTeX
@article{Repasky2026,
  author = {Repasky, Matthew and Wang, He and Xie, Yao},
  title = {Multi‐Agent Reinforcement Learning for Joint Police Patrol and Dispatch},
  journal = {Naval Research Logistics (NRL)},
  year = {2026},
  doi = {10.1002/nav.70059}
}
Kostenlos starten →