| 基于强化学习的多机器人协作 |
| |
| 引用本文： | 周浦城,洪炳镕,郭耸. 基于强化学习的多机器人协作[J]. 计算机工程与应用, 2005, 41(28): 10-12,90 |
| |
| 作者姓名： | 周浦城 洪炳镕 郭耸 |
| |
| 作者单位： | 哈尔滨工业大学计算机科学与工程系,哈尔滨,150001;哈尔滨工程大学计算机与技术学院,哈尔滨,150001 |
| |
| 基金项目： | 国家自然科学基金资助项目（编号：69985002） |
| |
| 摘 要： | 提出了一种动态环境下多个机器人获取合作行为的强化学习方法,该方法采用基于瞬时奖励的Q-学习完成单个机器人的学习,并利用人工势场法的思想确定不同机器人的学习顺序,在此基础上采用交替学习来完成多机器人的学习过程。试验结果表明所提方法的可行性和有效性。
|
| 关 键 词： | 多机器人系统 机器人足球 强化学习 协作 |
| 文章编号： | 1002-8331-（2005）28-0010-03 |
| 收稿时间： | 2005-07-01 |
| 修稿时间： | 2005-07-01 |
Multi-Robot Cooperation Based on Reinforcement Learning |
| |
| Zhou Pucheng,Hong Bingrong,Guo Song. Multi-Robot Cooperation Based on Reinforcement Learning[J]. Computer Engineering and Applications, 2005, 41(28): 10-12,90 |
| |
| Authors: | Zhou Pucheng Hong Bingrong Guo Song |
| |
| Affiliation: | 1.Department of Computer Science and Engineering,Harbin Institute of Technology,Harbin 150001; 2.School of Computer Science and Technology,Harbin Engineering University,Harbin 150001 |
| |
| Abstract: | In this paper,a kind of reinforcement learning method is addressed to obtain cooperative behaviors for multiple robots under dynamic environment.The proposed learning method adopts Q-learning with immediate reward,and determines learning order for different robots by virtue of the idea of artificial potential field.Based on these modifications,an alternative learning process is introduced to finish the learning process among multiple robots.Experimental results have shown the feasibility and validity of the given approach. |
| |
| Keywords: | multi-robot system robot soccer reinforcement learning cooperation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
