| 一种自适应强化学习算法在状态空间构建中的应用 |
| |
| 引用本文： | 程玉虎,王雪松,孙伟.一种自适应强化学习算法在状态空间构建中的应用[J].系统仿真学报,2006,18(1):188-191. |
| |
| 作者姓名： | 程玉虎 王雪松 孙伟 |
| |
| 作者单位： | 中国矿业大学信息与电气工程学院,江苏徐州,221008 |
| |
| 基金项目： | 中国矿业大学校科研和教改项目 |
| |
| 摘 要： | 针对模型未知以及具有连续状态的系统控制问题,提出一种基于强化学习的自适应控制策略。在Actor-Critic框架下,建立归一化径向基网络的自适应调节机制,实现未知系统状态空间的动态创建。有效克服了状态空间分割所带来的维度灾难,而且能够使得系统的结构总保持在最佳状态。通过对倒立摆控制的仿真研究验证了方法的有效性。
|
| 关 键 词： | 归一化径向基网络 Actor-Critic学习 状态空间构建 倒立摆 |
| 文章编号： | 1004-731X（2006）01-0188-04 |
| 收稿时间： | 2004-05-21 |
| 修稿时间： | 2005-10-09 |
Application of Adaptive Reinforcement Learning for State Space Construction |
| |
| CHENG Yu-hu,WANG Xue-song,SUN Wei.Application of Adaptive Reinforcement Learning for State Space Construction[J].Journal of System Simulation,2006,18(1):188-191. |
| |
| Authors: | CHENG Yu-hu WANG Xue-song SUN Wei |
| |
| Institution: | School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou 221008, China |
| |
| Abstract: | In order to solve the control problem for unknown model system with continuous state,an adaptive control strategy based on reinforcement learning was proposed.Under the Actor-Critic architecture,the adaptive adjustment mechanism for normalized radial basis function network was established to realize the state space construction dynamically.This approach could overcome the curse of dimensionality caused by state space division effectively and make the system structure always stay the optimal status.Simulation research for inverted pendulum control demonstrates the validity of the proposed method. |
| |
| Keywords: | normalized RBF network Actor-Critic learning state space construction inverted pendulum |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
