计算机应用研究2024，Vol.41Issue(1)：165-169,5.DOI:10.19734/j.issn.1001-3695.2023.04.0187
结合模糊控制的深度强化学习交通灯控制策略
Deep reinforcement learning traffic light control strategy combined with fuzzy control
摘要
Abstract
Most of the existing traffic light control strategies consider a single factor such as traffic flow,which is difficult to adapt to the dynamic states of the road networks.In order to solve this problem,this paper proposed a deep reinforcement lear-ning traffic light control strategy combined with fuzzy control,used SAC deep reinforcement learning to jointly optimize the phase selection and timing of traffic lights at two intersections,while considering multiple influencing factors,used fuzzy control to process the penalty function of SAC.The experimental results demonstrate that compared with the fixed cycle strategy,SAC control strategy and DDPG control strategy,the proposed traffic signal control strategy can obtain faster vehicle speed,and the fuel consumption and exhaust emissions of the vehicle are also improved.关键词
智能交通/交通信号灯控制/深度强化学习/模糊控制/VISSIMKey words
intelligent transportation/traffic signal control/deep reinforcement learning/fuzzy control/VISSIM分类
信息技术与安全科学引用本文复制引用
秦侨,杨超,杨海涛,黄旭民,张斌,杨海森..结合模糊控制的深度强化学习交通灯控制策略[J].计算机应用研究,2024,41(1):165-169,5.基金项目
国家自然科学基金资助项目-广东大数据科学中心项目(U1911401) （U1911401）
广东省自然科学基金面上项目(2019A1515011114) （2019A1515011114）
