Learning to send reinforcements: Coordinating multi-agent dynamic police patrol dispatching and rescheduling via reinforcement learning

• Main Authors: JOE, Waldy, LAU, Hoong Chuin
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Agent-based and Multi-agent Systems; Multi-agent learning Planning and Scheduling; Learning in planning and scheduling; police agents; Artificial Intelligence and Robotics; Operations Research, Systems Engineering and Industrial Engineering; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/8103; https://ink.library.smu.edu.sg/context/sis_research/article/9106/viewcontent/SendReinforcements_pvoa.pdf
• Institution: Singapore Management University

We address the problem of coordinating multiple agents in a dynamic police patrol scheduling via a Reinforcement Learning (RL) approach. Our approach utilizes Multi-Agent Value Function Approximation (MAVFA) with a rescheduling heuristic to learn dispatching and rescheduling policies jointly. Often,...