| 基于蒙特卡罗学习的多机器人自组织协作 |
| |
| 引用本文： | 周 彤,洪炳镕,朴松昊,周洪玉. 基于蒙特卡罗学习的多机器人自组织协作[J]. 计算机工程与应用, 2007, 43(30): 23-25 |
| |
| 作者姓名： | 周 彤 洪炳镕 朴松昊 周洪玉 |
| |
| 作者单位： | 哈尔滨工业大学,计算机科学与技术学院,哈尔滨,150001;哈尔滨理工大学,机械动力学院,哈尔滨,150080 |
| |
| 基金项目： | 国家自然科学基金 , 国家高技术研究发展计划(863计划) |
| |
| 摘 要： | 强化学习是提高机器人完成任务效率的有效方法,目前比较流行的学习方法一般采用累积折扣回报方法,但平均值回报在某些方面更适于多机器人协作。累积折扣回报方法在机器人动作层次上可以提高性能,但在多机器人任务层次上却不会得到很好的协作效果,而采用平均回报值的方法,就可以改变这种状态。本文把基于平均值回报的蒙特卡罗学习应用于多机器人合作中,得到很好的学习效果,实际机器人实验结果表明,采用平均值回报的方法优于累积折扣回报方法。
|
| 关 键 词： | 强化学习 多机器人 协作 蒙特卡罗学习 Q学习 |
| 文章编号： | 1002-8331（2007）30-0023-03 |
| 修稿时间： | 2007-07-01 |
Self-organizing coordination of multi-robot based on Monte Carlo learning |
| |
| ZHOU Tong,HONG Bing-rong,PIAO Song-hao,ZHOU Hong-yu. Self-organizing coordination of multi-robot based on Monte Carlo learning[J]. Computer Engineering and Applications, 2007, 43(30): 23-25 |
| |
| Authors: | ZHOU Tong HONG Bing-rong PIAO Song-hao ZHOU Hong-yu |
| |
| Affiliation: | 1.School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001,China 2.School of Mechanical and Power Engineering,Harbin University of Science and Technology,Harbin 150080,China |
| |
| Abstract: | Reinforcement learning is an effective way for accomplishing task in multi-robot system.While much of the work has focused On optimizing discounted cumtilative reward,optimizing average reward is sometimes a more suitable criterion for multi-robot coordination.Learning algorithms based on discounted rewards,such as Q learning,can attain a well result at the action-level,but it cannot perform well at the task-level.However,learning methods based on average reward,such as the Monte Carlo algorithm,are capable of achieving the optimal result through cooperation at the task-level.Real robot experiment shows that the algorithm adopting the average reward is superior to the one adopting the discounted cumulative reward. |
| |
| Keywords: | reinforcement learning multi-robot coordination Monte Carlo learning Q learning |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
|
