计算机应用研究2024，Vol.41Issue(6)：1618-1627,10.DOI:10.19734/j.issn.1001-3695.2023.08.0419
大规模智慧交通信号控制中的强化学习和深度强化学习方法综述
Review of reinforcement learning and deep reinforcement learning methods in large-scale intelligent traffic signal control
摘要
Abstract
At present,it is a general trend to introduce intelligent detection and control into traffic signal control system,es-pecially reinforcement learning and deep reinforcement learning methods show great technical advantages in scalability,stabili-ty and extensibility,and have become a research hotspot in this field.This paper studied traffic signal control tasks based on reinforcement learning,systematically sorted out the classification and application of reinforcement learning and deep reinforce-ment learning in the field of intelligent traffic signal control on the basis of extensive research results on traffic signal control methods,and summarized feasible solutions to large-scale traffic signal control problems by using multi-agent cooperation.This paper classified and summarized the factors affecting the traffic scene of large-scale traffic signal control,put forward the cur-rent challenges and potential research directions in this field from the perspective of improving the performance of traffic signal controllers.关键词
智能交通/交通信号控制/强化学习/交通信号灯/多智能体/大规模交通网络Key words
intelligent transportation/traffic signal control/reinforcement learning/traffic light/multiple agents/large-scale traffic network分类
信息技术与安全科学引用本文复制引用
翟子洋,郝茹茹,董世浩..大规模智慧交通信号控制中的强化学习和深度强化学习方法综述[J].计算机应用研究,2024,41(6):1618-1627,10.基金项目
国家重点研发计划资助项目(2021YFA1000300,2021YFA1000303) （2021YFA1000300,2021YFA1000303）
国家青年基金资助项目(202006565013) （202006565013）
