| 基于量子理论及蚁群算法的多Agent Q学习 |
| |
| 引用本文： | 孟祥萍,王圣镔.基于量子理论及蚁群算法的多Agent Q学习[J].计算机工程与应用,2010,46(21):43-46. |
| |
| 作者姓名： | 孟祥萍 王圣镔 |
| |
| 作者单位： | 1. 长春工程学院,电气与信息学院,长春,130012
2. 东北电力大学,信息工程学院,吉林,132012 |
| |
| 基金项目： | 吉林省科技发展计划项目，吉林省教育厅重点科技计划项目及教科合字[2008]第201号 |
| |
| 摘 要： | 针对多Agent协作强化学习中存在的行为和状态维数灾问题，以及行为选择上存在多个均衡解，为了收敛到最佳均衡解需要搜索策略空间和协调策略选择问题，提出了一种新颖的基于量子理论和蚁群算法的多Agent协作学习算法。新算法首先借签了量子计算理论，将多Agent的行为和状态空间通过量子叠加态表示，利用量子纠缠态来协调策略选择，利用概率振幅进行动作探索，加快学习速度。其次，根据蚁群算法，提出“脚印”思想来间接增强Agent之间的交互。最后，对新算法的理论分析和实验结果都证明了改进的Q学习是可行的，并且可以有效地提高学习效率。
|
| 关 键 词： | 多Agent系统 协作 量子计算 Q-学习 均衡解 蚁群算法 |
| 收稿时间： | 2009-1-21 |
| 修稿时间： | 2009-4-24
|
Multi-Agent Q-learning based on quantum theory and ant colony algorithm |
| |
| MENG Xiang-ping,WANG Sheng-bin.Multi-Agent Q-learning based on quantum theory and ant colony algorithm[J].Computer Engineering and Applications,2010,46(21):43-46. |
| |
| Authors: | MENG Xiang-ping WANG Sheng-bin |
| |
| Affiliation: | 1.Department of Electrical Engineering,Changchun Institute of Technology,Changchun 130012,China 2.Department of Computer Engineering,Northeast Dianli University,Jilin 132012,China) |
| |
| Abstract: | Due to the interactions among the Agents in the cooperative multi-Agent systems,multi-Agent learning problem complexity can rise rapidly with the number of Agents or their behavioral sophistication.In order to converge to desirable equilibrium,Agents generally require sufficient exploration of strategy space and coordinate their policies to achieve optimal equilibrium.A novel cooperative multi-Agent learning method is proposed based on quantum theory,ant algorithm and Q-learning.First,this method not only coordinates Agents＇behaviors using quantum entanglement and helps Agents make action selection under quantum superposition,but also adopts Grover＇s searching algorithm which can probe the action,speed up learn-ing.Second,according to ant algorithm,footmark thought is presented so that Agents can be indirectly enforced to communicate with others.At last,the theory analysis and result of experiment both demonstrate that the improved Q-learning is feasible and increases the learning efficiency. |
| |
| Keywords: | multi-Agent system cooperative quantum computing Q-learning equilibrium ant colony algorithm |
| 本文献已被 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 |
|
