| 基于Q-Learning的智能体训练 |
| |
| 引用本文： | 赵增荣,韩提文. 基于Q-Learning的智能体训练[J]. 石家庄铁道学院学报, 2007, 20(2): 37-39,72 |
| |
| 作者姓名： | 赵增荣 韩提文 |
| |
| 作者单位： | [1]河北师范大学职业技术学院,河北石家庄050031 [2]河北工业职业技术学院成教部,河北石家庄050030 |
| |
| 基金项目： | 河北师范大学校科研和教改项目 |
| |
| 摘 要： | 针对机器人足球比赛的多智能体环境下智能体的训练问题,提出了一种将模糊控制与Q-Learning相结合的学习方法,并在学习过程中自动调节回报函数以获得最优策略,此方法的有效性在中型组的仿真平台上得到了验证,并取得了较好效果,还可将它改进应用于其他多智体环境。
|
| 关 键 词： | 模糊控制 回报函数 |
| 文章编号： | 1006-3226（2007）02-0037-04 |
| 收稿时间： | 2006-11-06 |
| 修稿时间： | 2006-11-06 |
How to Train the Agent Based on the Way of Q-Learning |
| |
| Zhao Zengrong,Han Tiwen. How to Train the Agent Based on the Way of Q-Learning[J]. Journal of Shijiazhuang Railway Institute, 2007, 20(2): 37-39,72 |
| |
| Authors: | Zhao Zengrong Han Tiwen |
| |
| Affiliation: | 1. College of Vocation and Technology, Hebei Normal University, Shijiazhuang 050031, China; 2. The Adults Education Department of Hebei Industrial Vocational Technology College, Shijiazhuang 050030, China |
| |
| Abstract: | In order to solve the problem of agent training in the multi-agent circumstances of robot soccer, a new method of agent learning is put forward, which combines the fuzzy control with the Q-Learning. During the learning process, the reward function is controlled automatically to earn the optimal policy. It is proved that this method is effective on the simulation platform of middle-size league, and the simulation result is good. In addition, it could be adapted to apply in other multi-agent circumstances. |
| |
| Keywords: | Q-Learning |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
