Advanced Policy Learning Near-Optimal Regulation

作     者：Ding Wang Xiangnan Zhong 

作者机构：IEEE the Faculty of Information Technology Beijing University of Technology and also with the Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology the Department of Electrical Engineering University of North Texas 

出 版 物：《IEEE/CAA Journal of Automatica Sinica》 (自动化学报（英文版）)

年 卷 期：2019年第6卷第3期

页      面：743-749页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 

基　　金：supported in part by the National Natural Science Foundation of China(61773373,U1501251,61533017) in part by the Young Elite Scientists Sponsorship Program by the China Association for Science and Technology in part by the Youth Innovation Promotion Association of the Chinese Academy of Sciences 

主　　题：Adaptive critic algorithm learning control neural approximation nonaffine dynamics optimal regulation 

摘      要：Designing advanced design techniques for feedback stabilization and optimization of complex systems is important to the modern control field. In this paper, a near-optimal regulation method for general nonaffine dynamics is developed with the help of policy learning. For addressing the nonaffine nonlinearity, a pre-compensator is constructed, so that the augmented system can be formulated as affine-like form. Different cost functions are defined for original and transformed controlled plants and then their relationship is analyzed in detail. Additionally, an adaptive critic algorithm involving stability guarantee is employed to solve the augmented optimal control problem. At last, several case studies are conducted for verifying the stability, robustness, and optimality of a torsional pendulum plant with suitable cost.