| 改进的Q学习算法及在其RoboCup中的应用 |
| |
| 引用本文： | 周燕艳.改进的Q学习算法及在其RoboCup中的应用[J].四川理工学院学报(自然科学版),2011,24(4):417-421. |
| |
| 作者姓名： | 周燕艳 |
| |
| 作者单位： | [1]合肥工业大学计算机与信息学院,合肥230001;[2]铜陵学院数学与计算机系,安徽铜陵244000 |
| |
| 摘 要： | 传统的Q学习已被有效地应用于处理RoboCup中传球策略问题,但是它仅能简单地离散化连续的状态、动作空间。文章提出一种改进的Q学习算法,提出将神经网络应用于Q学习,系统只需学习部分状态—动作的Q值,即可进行Q学习,有效的提高收敛的速度。最后在RoboCup环境中验证这个算法,对传球成功率有所提高。
|
| 关 键 词： | RoboCup 神经网络 Q学习 智能体 |
Improved Q-learning Algorithm and Its Application in RoboCup Environment |
| |
| ZHOU Yan-yan.Improved Q-learning Algorithm and Its Application in RoboCup Environment[J].Journal of Sichuan University of Science & Engineering:Natural Science Editton,2011,24(4):417-421. |
| |
| Authors: | ZHOU Yan-yan |
| |
| Institution: | ZHOU Yan-yan1,2(1.School of Computer and Information,Hefei University of Technology,Hefei 230001,China;2.Department of Mathematics and Computer,Tongling College,Tongling 244000,China) |
| |
| Abstract: | Q-learning has traditionally been used effectively in dealing with RoboCup ball tactics,but it is only a simple discretization of continuous state and action space.Proposed a modified Q learning algorithm,neural network applied to Q learning,the system only need to learn some of the state-action Q value,you can get a continuous approximation of Q value,and can effectively improve generalization ability.Finally,in the RoboCup environment,the algorithm is proved to achieve optimal playing strategy,and effectively improves the success rate of passing ball. |
| |
| Keywords: | RoboCup neural network Q learning Agent |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
