Learning to Send Reinforcements: Coordinating Multi-Agent Dynamic Police Patrol Dispatching and Rescheduling via Reinforcement Learning.
Waldy JoeHoong Chuin LauPublished in: IJCAI (2023)
Keyphrases
- reinforcement learning
- multi agent
- learning process
- learning algorithm
- learning agents
- supervised learning
- learning systems
- prior knowledge
- learning problems
- active learning
- machine learning
- function approximation
- evolutionary learning
- dynamic environments
- optimal policy
- markov decision processes
- manufacturing systems
- model free
- temporal difference
- autonomous learning
- multi agent environments