| 多Agent系统中Q学习算法研究 |
| |
| 引用本文： | 战忠丽,王强,王佩霞. 多Agent系统中Q学习算法研究[J]. 辽宁农业职业技术学院学报, 2008, 10(5): 48-50 |
| |
| 作者姓名： | 战忠丽 王强 王佩霞 |
| |
| 作者单位： | 辽宁农业职业技术学院,辽宁,营口,115009;吉林电子信息职业技术学院,吉林,吉林,132021 |
| |
| 摘 要： | 为了提高多Agent系统中的典型的强化学习——Q学习的学习效率和收敛速度,充分利用环境信息和相关的专家经验,提出了改进的多Agent系统强化学习算法（Q学习算法）。该算法通过Agent间对信息的共享,有效地将Q学习算法扩展应用到多Agent系统中。
|
| 关 键 词： | 强化学习 Q学习 多Agent系统 |
Q-Learning in Multi-Agent Systems |
| |
| ZHAN Zhong-li,WANG Qiang,WANG Pei-xia. Q-Learning in Multi-Agent Systems[J]. Journal of Liaoning Agricultural Vocation-Technical College, 2008, 10(5): 48-50 |
| |
| Authors: | ZHAN Zhong-li WANG Qiang WANG Pei-xia |
| |
| Affiliation: | ZHAN Zhong - li, WANG Qiang, WANG Peixia (1. Jilin Technology University of Electric Information,Jilin 132012, China 2. Liaoning Agricultural College,Yingkou, 115009, China ) |
| |
| Abstract: | Reinforcement Learning(RL)is an important branch of machine learning and Q-learning is a typical RL.The learning process adjusts its actions according to external signals from interactions with the environment.I proposed a improved Multi-Agent System Reinforcement Learning Algorithm,which can extend Q-Learning Algorithm to Multi-Agent System via sharing all of Agents' information. |
| |
| Keywords: | RL QL MAS |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
