| 基于场景任务划分的多智能体Q-学习研究 |
| |
| 引用本文： | 刘亮,李龙澍.基于场景任务划分的多智能体Q-学习研究[J].计算机工程与应用,2009,45(21):21-24. |
| |
| 作者姓名： | 刘亮 李龙澍 |
| |
| 作者单位： | 安徽大学,计算智能与信号处理教育部重点实验室,合肥,230039 |
| |
| 基金项目： | 国家自然科学基金，安徽省高校学科拔尖人才基金 |
| |
| 摘 要： | 从研究分层强化学习入手,提出由MAS中任务结构分析产生的分层合作研究方法,通过区分子任务并以此建立更大粒度层面上的基于任务场景的状态空间,并结合以联合动作为基础的任务动作与势能场模型,从而解决强化学习中的状态空间的维数灾难。文中给出了基于机器人足球的子任务的算法应用,其效能得到实验的验证。
|
| 关 键 词： | 多Agent系统 强化学习 Q-学习 任务场景 |
| 收稿时间： | 2009-4-8 |
| 修稿时间： | 2009-5-14
|
Multi-agent Q-learning based on mission scenarios division |
| |
| LIU Liang,LI Long-shu.Multi-agent Q-learning based on mission scenarios division[J].Computer Engineering and Applications,2009,45(21):21-24. |
| |
| Authors: | LIU Liang LI Long-shu |
| |
| Affiliation: | LIU Liang,LI Long-shu Key Lab of IC&SP at Anhui University,Ministry of Education,Hefei 230039,China |
| |
| Abstract: | From the study of layered reinforcement learning approach,this paper proposes layered collaboration research methods through the mission structure analysis in MAS.By distinguishing the sub-mission,the state space is built,which is in greater level of granularity and based on the mission effect,combining with the mission action based on joint action and potential field model so as to solve the dimensional disaster in state space of reinforcement learning.This paper provides application of the algorithm based... |
| |
| Keywords: | Multi-Agent System (MAS) reinforcement learning Q-learning mission scenarios |
| 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》下载全文 |
|
