| 基于车均延误最小的Q学习交通信号控制方法 |
| |
| 引用本文： | 沈文,李志强.基于车均延误最小的Q学习交通信号控制方法[J].长沙交通学院学报,2009,25(3). |
| |
| 作者姓名： | 沈文 李志强 |
| |
| 作者单位： | 长沙理工大学,公路工程省部共建教育部重点实验室,湖南,长沙,410004 |
| |
| 基金项目： | 湖南省教育厅科研资助项目，长沙理工大学公路工程省部共建教育部重点实验室开放基金资助项目 |
| |
| 摘 要： | 为了检测Q学习算法在信号控制方案中的效果,在Webster配时法的基础上,建立了适应交通信号控制及以车均延误最小为目标的奖惩函数,并详细说明了Q学习独立交叉口信号控制的原理和应用过程.通过流量波动大和小两个算例,验证了Q学习控制优于定时控制.
|
| 关 键 词： | 交通信号控制 Q学习 智能体 |
Q-learning traffic signal control based on the minimization of average delay |
| |
| SHEN Wen,LI Zhi-qiang.Q-learning traffic signal control based on the minimization of average delay[J].Journal of Changsha Communications University,2009,25(3). |
| |
| Authors: | SHEN Wen LI Zhi-qiang |
| |
| Institution: | SHEN Wen,LI Zhi-qiang(Key Laboratory for Highway Engineering of Ministry of Education Built by Province , Ministry,Changsha University of Science & Technology,Changsha 410004,China) |
| |
| Abstract: | The goal of the paper is to detect the effect of Q-learning method on traffic signal control.Based on Webster's timing algorithm,a reward-penalty function adaptable to traffic signal control for the minimization of average delay is estabilished.It also illustrates the control theory and application process of Q-learning signal control in single intersection.From the two examples in large and small flow fluctuation,the author verified that Q-learning control is better than fixed-time control. |
| |
| Keywords: | traffic signal control Q-learning agents |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
