A new accelerating algorithm for multi-agent reinforcement learning
文献类型：期刊论文
| 作者 | Zhang RB(张汝波); Zhong Y(仲宇); Gu GC(顾国昌) |
| 刊名 | Journal of Harbin Institute of Technology
 |
| 出版日期 | 2005 |
| 卷号 | 12期号:1页码:48-51 |
| 关键词 | distributed reinforcement learning accelerating algorithm machine learning multi-agent system |
| ISSN号 | 1005-9113 |
| 产权排序 | 2 |
| 中文摘要 | In multi-agent systems, joint-action must be employed to achieve cooperation because the evaluation of the behavior of an agent often depends on the other agents' behaviors. However, joint -action reinforcement learning algorithms suffer the slow convergence rate because of the enormous learning space produced by jointaction. In this article, a prediction-based reinforcement learning algorithm is presented for multi-agent cooperation tasks, which demands all agents to learn predicting the probabilities of actions that other agents may execute. A multi-robot cooperation experiment is run to test the efficacy of the new algorithm, and the experiment results show that the new algorithm can achieve the cooperation policy much faster than the primitive reinforcement learning algorithm. |
| 收录类别 | EI |
| 资助信息 | SponsoredbyRobotics Laboratory;; Shenyang Institute of Automation;; Chinese Academy of Sciences Foundation(GrantNo. RL200106). |
| 语种 | 英语 |
| 公开日期 | 2012-05-29 |
| 源URL | [http://ir.sia.cn/handle/173321/7280]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 推荐引用方式 GB/T 7714 | Zhang RB,Zhong Y,Gu GC. A new accelerating algorithm for multi-agent reinforcement learning[J]. Journal of Harbin Institute of Technology,2005,12(1):48-51. |
| APA | Zhang RB,Zhong Y,&Gu GC.(2005).A new accelerating algorithm for multi-agent reinforcement learning.Journal of Harbin Institute of Technology,12(1),48-51. |
| MLA | Zhang RB,et al."A new accelerating algorithm for multi-agent reinforcement learning".Journal of Harbin Institute of Technology 12.1(2005):48-51. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。