CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 平行控制
Error Bound Analysis of Q-Function for Discounted Optimal Control Problems With Policy Iteration
Yan, Pengfei1; Wang, Ding1; Li, Hongliang2; Liu, Derong3
Source PublicationIEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
2017-07-01
Volume47Issue:7Pages:1207-1216
SubtypeArticle
AbstractIn this paper, we present error bound analysis of the Q-function for the action-dependent adaptive dynamic programming for solving discounted optimal control problems of unknown discrete-time nonlinear systems. The convergence of Q-functions derived by a policy iteration algorithm under ideal conditions is given. Considering the approximated errors of the Q-function and control policy in the policy evaluation step and policy improvement step, we establish error bounds of approximate Q-functions in each iteration. With the given boundedness conditions, the approximate Q-function will converge to a finite neighborhood of the optimal Q-function. To implement the presented algorithm, two three-layer neural networks are employed to approximate the Q-function and the control policy, respectively. Finally, a simulation example is utilized to verify the validity of the presented algorithm.
KeywordAdaptive Dynamic Programming (Adp) Error Analysis Nonlinear Systems Policy Iteration Q-function
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TSMC.2016.2563982
WOS KeywordTIME NONLINEAR-SYSTEMS ; APPROXIMATE VALUE-ITERATION ; UNKNOWN INTERNAL DYNAMICS ; ADAPTIVE OPTIMAL-CONTROL ; OPTIMAL-CONTROL DESIGN ; H-INFINITY CONTROL ; ZERO-SUM GAMES ; INPUT CONSTRAINTS ; HJB SOLUTION ; REINFORCEMENT
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China(61233001 ; Beijing Natural Science Foundation(4162065) ; Early Career Development Award of SKLMCCS ; 61273140 ; 61304086 ; 61374105 ; 61533017 ; U1501251)
WOS Research AreaAutomation & Control Systems ; Computer Science
WOS SubjectAutomation & Control Systems ; Computer Science, Cybernetics
WOS IDWOS:000404354600014
Citation statistics
Cited Times:4[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/15223
Collection复杂系统管理与控制国家重点实验室_平行控制
Affiliation1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.IBM Res China, Beijing 100193, Peoples R China
3.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
Recommended Citation
GB/T 7714
Yan, Pengfei,Wang, Ding,Li, Hongliang,et al. Error Bound Analysis of Q-Function for Discounted Optimal Control Problems With Policy Iteration[J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,2017,47(7):1207-1216.
APA Yan, Pengfei,Wang, Ding,Li, Hongliang,&Liu, Derong.(2017).Error Bound Analysis of Q-Function for Discounted Optimal Control Problems With Policy Iteration.IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,47(7),1207-1216.
MLA Yan, Pengfei,et al."Error Bound Analysis of Q-Function for Discounted Optimal Control Problems With Policy Iteration".IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 47.7(2017):1207-1216.
Files in This Item: Download All
File Name/Size DocType Version Access License
[00-J-2017-TSMC] Err(625KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yan, Pengfei]'s Articles
[Wang, Ding]'s Articles
[Li, Hongliang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yan, Pengfei]'s Articles
[Wang, Ding]'s Articles
[Li, Hongliang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yan, Pengfei]'s Articles
[Wang, Ding]'s Articles
[Li, Hongliang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: [00-J-2017-TSMC] Error bound analysis of Q-function for discounted optimal control problems with policy iteration.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.