Multi-Agent Reinforcement Learning for Joint Police Patrol and Dispatch
This addresses a practical problem for police operations by integrating two previously separate decision-making processes, though it is incremental as it builds on existing reinforcement learning methods.
The paper tackles the problem of jointly optimizing police patrol and dispatch decisions to improve operational efficiency and reduce emergency response times, demonstrating that their multi-agent reinforcement learning approach outperforms policies optimized for patrol or dispatch alone.
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. Methodology/results: 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 Q-learner (agent) with a shared deep Q-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. Managerial Implications: 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.