A new self-learning optimal control laws for a class of discrete-time nonlinear systems based on ESN architecture  

作　　者：SONG RuiZhuo XIAO WenDong SUN ChangYin 

机构地区：[1]School of Automation and Electrical Engineering,University of Science and Technology Beijing

出　　处：《Science China(Information Sciences)》2014年第6期280-289,共10页中国科学（信息科学）（英文版）

基　　金：supported by the National Natural Science Foundation of China(Grant Nos.61304079,61125306,61034002);Beijing Natural Science Foundation(Grant No.4143065);China Postdoctoral Science Foundation(Grant No.2013M530527);the Open Research Project from SKLMCCS(Grant No.20120106)

摘　　要：A novel self-learning optimal control method for a class of discrete-time nonlinear systems is proposed based on iteration adaptive dynamic programming（ADP）algorithm.It is proven that the iteration costate functions converge to the optimal one,and a detailed convergence analysis of the iteration ADP algorithm is given.Furthermore,echo state network（ESN）architecture is used as the approximator of the costate function for each iteration.To ensure the reliability of the ESN approximator,the ESN mean square training error is constrained in the satisfactory range.Two simulation examples are given to demonstrate that the proposed control method has a fast response speed due to the special structure and the fast training process.A novel self-learning optimal control method for a class of discrete-time nonlinear systems is proposed based on iteration adaptive dynamic programming（ADP）algorithm.It is proven that the iteration costate functions converge to the optimal one,and a detailed convergence analysis of the iteration ADP algorithm is given.Furthermore,echo state network（ESN）architecture is used as the approximator of the costate function for each iteration.To ensure the reliability of the ESN approximator,the ESN mean square training error is constrained in the satisfactory range.Two simulation examples are given to demonstrate that the proposed control method has a fast response speed due to the special structure and the fast training process.

关 键 词：adaptive dynamic programming DISCRETE-TIME optimal control ESN costate function 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]