| 多智能体Q学习在多AUV协调中的应用研究 |
| |
| 引用本文： | 严浙平,李锋,黄宇峰.多智能体Q学习在多AUV协调中的应用研究[J].应用科技,2008,35(1):57-60. |
| |
| 作者姓名： | 严浙平 李锋 黄宇峰 |
| |
| 作者单位： | 哈尔滨工程大学,自动化学院,黑龙江,哈尔滨,150001 |
| |
| 基金项目： | 黑龙江省博士后科研启动基金 |
| |
| 摘 要： | 分析了近年来提出的几种主要单、多智能体强化算法,提出一种多智能体Q学习算法,并将它用于多AUV协调中.此算法融合了Nash-Q、CE-Q及WoLF-PHC的算法思想或表达形式,程序简单、容易计算,并且具有很好的收敛性.多AUV协调控制仿真实验结果表明这个算法是有效的.
|
| 关 键 词： | 多智能体 Q学习 Nash均衡 多AUV 多智能体 学习算法 协调控制 应用 研究 coordination algorithm application 结果 仿真实验 收敛性 计算 程序 表达形式 算法思想 算法融合 强化 分析 |
| 文章编号： | 1009-671X（2008）01-0057-04 |
| 收稿时间： | 2007-10-17 |
| 修稿时间： | 2007年10月17 |
Research on application of multi-agent Q-learning algorithm in multi-AUV coordination |
| |
| YAN Zhe-ping,LI Feng,HUANG YU-feng.Research on application of multi-agent Q-learning algorithm in multi-AUV coordination[J].Applied Science and Technology,2008,35(1):57-60. |
| |
| Authors: | YAN Zhe-ping LI Feng HUANG YU-feng |
| |
| Abstract: | Several major reinforcement learning algorithms for single agent and multi-agents, that are developed in recent years, are investigated, compared and analyzed. A multi-agent Q-learning algorithm is proposed and used in muhi-AUV coordination. This algorithm combines the thoughts or expressions of Nash-Q, CE-Q and WoLF-PHC algorithms, so that the program is simple, the computation is easy, and the convergence rate is high. Experiment results of muhi-AUV coordination and control prove the effectiveness of this algorithm. |
| |
| Keywords: | multi-agent Q-learning Nash equilibrium multi-AUV |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
