| 一种交通信号自学习控制方法 |
| |
| 引用本文： | 常歆识,承向军,刘军.一种交通信号自学习控制方法[J].铁路计算机应用,2006,15(2):51-53. |
| |
| 作者姓名： | 常歆识 承向军 刘军 |
| |
| 作者单位： | 北京交通大学,软件学院,北京,100044%北京交通大学,交通运输学院,北京,100044 |
| |
| 摘 要： | 基于智能体的信号控制方法已经成为研究热点之一,目前遗传算法已被用来实现agent的自学习,论文将Q-学习应用在城市交通控制中,用来解决单路口信号控制agent的自学习问题,经过仿真试验,并与遗传算法的结果相对比,证明此方法的控制效果较好.
|
| 关 键 词： | 智能体 Q-学习 交通控制 方法 |
| 文章编号： | 1005-8451(2006)02-0051-03 |
| 收稿时间： | 2005-10-19 |
| 修稿时间： | 2005年10月19 |
Method of self-learning traffic signal control |
| |
| CHANG Xin-shi,CHENG Xiang-jun,LIU Jun.Method of self-learning traffic signal control[J].Railway Computer Application,2006,15(2):51-53. |
| |
| Authors: | CHANG Xin-shi CHENG Xiang-jun LIU Jun |
| |
| Institution: | 1.School ofSottware, Beijing Jiaotong University, Beijing 100044, China; 2.School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044 China |
| |
| Abstract: | The research on intelligent signal control had attracted much attention of experts and scholars. Genetic algonmm was already used for self-learning of agent. It was researched Q-learning method in urban traffic control for self-learning of signal control agent in an single intersection. This method was algorithm by simulation. |
| |
| Keywords: | agent Q-Learning traffic control method proved that it had a better control effect than genetic |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《铁路计算机应用》浏览原始摘要信息 |
| 点击此处可从《铁路计算机应用》下载免费的PDF全文 |
|
