作者其他论文
文献详情
Reinforcement Learning Output Feedback NN Control Using Deterministic Learning Technique
文献类型:期刊
作者:Xu, Bin[1]  Yang, Chenguang[2]  Shi, Zhongke[3]  
机构:[1]Northwestern Polytech Univ, Sch Automat, Xian 710072, Peoples R China.;
[2]Univ Plymouth, Sch Comp & Math, Plymouth PL4 8AA, Devon, England.,Beijing Inst Technol, Sch Automat, Beijing 100086, Peoples R China.;
[3]Northwestern Polytech Univ, Sch Automat, Xian 710072, Peoples R China.;
通讯作者:Xu, B (reprint author), Northwestern Polytech Univ, Sch Automat, Xian 710072, Peoples R China.
年:2014
期刊名称:IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS影响因子和分区
卷:25
期:3
页码范围:635-641
学科:计算机科学
收录情况:SCI(E)(WOS:000331985500015)  EI(20141117440325)  ESI高被引论文(WOS:000331985500015)  
所属部门:自动化学院
重要成果类型:ESI高被引
被引频次:38
人气指数:5732
浏览次数:5622
基金:National Science Foundation of China [61304098, 61134004]; Foundation of Key Laboratory of Autonomous Systems and Networked Control (Ministry of Education, China) [2012A04]; EU [PIIFR-GA-2010-910078-H2R]; NWPU [JC20120236]
关键词:Approximate dynamic programming; discrete-time system; output feedback control; pure-feedback system; radial basis function neural network (RBF NN)
摘要:
In this brief, a novel adaptive-critic-based neural network (NN) controller is investigated for nonlinear pure-feedback systems. The controller design is based on the transformed predictor form, and the actor-critic NN control architecture includes two NNs, whereas the critic NN is used to approximate the strategic utility function, and the action NN is employed to minimize both the strategic utility function and the tracking error. A deterministic learning technique has been employed to guarant ...More
0
评论(0 条评论)
登录