Adaptive Multi-Step Evaluation Design With Stability Guarantee for Discrete-Time Optimal Learning Control

This paper is concerned with a novel integrated multi-step heuristic dynamic programming (MsHDP) algorithm for solving optimal control problems. It is shown that, initialized by the zero cost function, MsHDP can converge to the optimal solution of the Hamilton-Jacobi-Bellman (HJB) equation. Then, th...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE/CAA journal of automatica sinica Jg. 10; H. 9; S. 1797 - 1809
Hauptverfasser:	Wang, Ding, Wang, Jiangyu, Zhao, Mingming, Xin, Peng, Qiao, Junfei
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Piscataway Chinese Association of Automation (CAA) 01.09.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Faculty of Information Technology,the Beijing Key Laboratory of Computational Intelligence and Intelligent System,the Beijing Laboratory of Smart Environmental Protection,and the Beijing Institute of Artificial Intelligence,Beijing University of Technology,Beijing 100124,China
Schlagworte:	Adaptive control Adaptive critic Algorithms artificial neural networks Convergence Cost function Dynamic programming Hamilton-Jacobi-Bellman (HJB) equation Heuristic algorithms Iterative methods Mathematical models multi-step heuristic dynamic programming multi-step reinforcement learning Neural networks Observers Optimal control Policies Stability analysis Stability criteria Time optimal control artificial neural networks Adaptive critic optimal control Hamilton-Jacobi-Bellman(HJB)equation multi-step heuristic dynamic pro-gramming multi-step reinforcement learning
ISSN:	2329-9266, 2329-9274
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	This paper is concerned with a novel integrated multi-step heuristic dynamic programming (MsHDP) algorithm for solving optimal control problems. It is shown that, initialized by the zero cost function, MsHDP can converge to the optimal solution of the Hamilton-Jacobi-Bellman (HJB) equation. Then, the stability of the system is analyzed using control policies generated by MsHDP.Also, a general stability criterion is designed to determine the admissibility of the current control policy. That is, the criterion is applicable not only to traditional value iteration and policy iteration but also to MsHDP. Further, based on the convergence and the stability criterion, the integrated MsHDP algorithm using immature control policies is developed to accelerate learning efficiency greatly. Besides, actor-critic is utilized to implement the integrated MsHDP scheme, where neural networks are used to evaluate and improve the iterative policy as the parameter architecture. Finally, two simulation examples are given to demonstrate that the learning effectiveness of the integrated MsHDP scheme surpasses those of other fixed or integrated methods.
AbstractList	This paper is concerned with a novel integrated multi-step heuristic dynamic programming(MsHDP)algorithm for solving optimal control problems.It is shown that,initialized by the zero cost function,MsHDP can converge to the optimal solution of the Hamilton-Jacobi-Bellman(HJB)equation.Then,the stability of the system is analyzed using control policies gener-ated by MsHDP.Also,a general stability criterion is designed to determine the admissibility of the current control policy.That is,the criterion is applicable not only to traditional value iteration and policy iteration but also to MsHDP.Further,based on the convergence and the stability criterion,the integrated MsHDP algorithm using immature control policies is developed to accel-erate learning efficiency greatly.Besides,actor-critic is utilized to implement the integrated MsHDP scheme,where neural net-works are used to evaluate and improve the iterative policy as the parameter architecture.Finally,two simulation examples are given to demonstrate that the learning effectiveness of the inte-grated MsHDP scheme surpasses those of other fixed or inte-grated methods. This paper is concerned with a novel integrated multi-step heuristic dynamic programming (MsHDP) algorithm for solving optimal control problems. It is shown that, initialized by the zero cost function, MsHDP can converge to the optimal solution of the Hamilton-Jacobi-Bellman (HJB) equation. Then, the stability of the system is analyzed using control policies generated by MsHDP.Also, a general stability criterion is designed to determine the admissibility of the current control policy. That is, the criterion is applicable not only to traditional value iteration and policy iteration but also to MsHDP. Further, based on the convergence and the stability criterion, the integrated MsHDP algorithm using immature control policies is developed to accelerate learning efficiency greatly. Besides, actor-critic is utilized to implement the integrated MsHDP scheme, where neural networks are used to evaluate and improve the iterative policy as the parameter architecture. Finally, two simulation examples are given to demonstrate that the learning effectiveness of the integrated MsHDP scheme surpasses those of other fixed or integrated methods.
Author	Qiao, Junfei Xin, Peng Wang, Ding Zhao, Mingming Wang, Jiangyu
AuthorAffiliation	Faculty of Information Technology,the Beijing Key Laboratory of Computational Intelligence and Intelligent System,the Beijing Laboratory of Smart Environmental Protection,and the Beijing Institute of Artificial Intelligence,Beijing University of Technology,Beijing 100124,China
AuthorAffiliation_xml	– name: Faculty of Information Technology,the Beijing Key Laboratory of Computational Intelligence and Intelligent System,the Beijing Laboratory of Smart Environmental Protection,and the Beijing Institute of Artificial Intelligence,Beijing University of Technology,Beijing 100124,China
Author_xml	– sequence: 1 givenname: Ding surname: Wang fullname: Wang, Ding email: dingwang@bjut.edu.cn organization: Beijing University of Technology,Faculty of Information Technology, the Beijing Key Laboratory of Computational Intelligence and Intelligent System, the Beijing Laboratory of Smart Environmental Protection, and the Beijing Institute of Artificial Intelligence,Beijing,China,100124 – sequence: 2 givenname: Jiangyu surname: Wang fullname: Wang, Jiangyu email: wangjiangyu@emails.bjut.edu.cn organization: Beijing University of Technology,Faculty of Information Technology, the Beijing Key Laboratory of Computational Intelligence and Intelligent System, the Beijing Laboratory of Smart Environmental Protection, and the Beijing Institute of Artificial Intelligence,Beijing,China,100124 – sequence: 3 givenname: Mingming surname: Zhao fullname: Zhao, Mingming email: zhaomm@emails.bjut.edu.cn organization: Beijing University of Technology,Faculty of Information Technology, the Beijing Key Laboratory of Computational Intelligence and Intelligent System, the Beijing Laboratory of Smart Environmental Protection, and the Beijing Institute of Artificial Intelligence,Beijing,China,100124 – sequence: 4 givenname: Peng surname: Xin fullname: Xin, Peng email: xinpeng@emails.bjut.edu.cn organization: Beijing University of Technology,Faculty of Information Technology, the Beijing Key Laboratory of Computational Intelligence and Intelligent System, the Beijing Laboratory of Smart Environmental Protection, and the Beijing Institute of Artificial Intelligence,Beijing,China,100124 – sequence: 5 givenname: Junfei surname: Qiao fullname: Qiao, Junfei email: adqiao@bjut.edu.cn organization: Beijing University of Technology,Faculty of Information Technology, the Beijing Key Laboratory of Computational Intelligence and Intelligent System, the Beijing Laboratory of Smart Environmental Protection, and the Beijing Institute of Artificial Intelligence,Beijing,China,100124
BookMark	eNp9kD1v2zAQhonABeK4nrNkINAtgJwjKUriaDgfTeDCg11kJCjpZDNQKJeikrq_vnJUJEWHLnc3vB-454yMXOOQkHMGM8ZAXT3M1zMOXMwYF0kWn5AxF1xFiqfx6P1OklMybdsnAGBcpomKx8TOS7MP9gXpt64ONloH3NObF1N3JtjG0Wts7dbRRxt2dB1MbmsbDvSuM964gEirxtNr2xYeA0Yb-4x01cc9m5ou0Xhn3ZYuGhd8U38mnypTtzj9syfk--3NZvE1Wq7u7hfzZVQILkOUIyQxGACVyJzlrFRcKOCciQLiOClTnqSmygrFMpVnaSUrEwOkULFSlsoUYkIuh9xX4yrjtvqp6bzrG_Wvcvcz14fX_EgKFPRzQr4M4r1vfnTYhg81zyQTsRSp7FVXg6rwTdt6rPTe9z_6g2agj_x1z18fU_XAv3fIfxyFDW9Egze2_o_vYvBZRPyrhTMFGRO_AURrkv0
CODEN	IJASJC
CitedBy_id	crossref_primary_10_1002_oca_3173 crossref_primary_10_1002_acs_3801 crossref_primary_10_1007_s11071_024_09778_3 crossref_primary_10_1002_rnc_7914 crossref_primary_10_1007_s11071_025_11608_z crossref_primary_10_1109_TII_2024_3452189 crossref_primary_10_1002_rnc_7834 crossref_primary_10_1016_j_engappai_2024_109756 crossref_primary_10_1016_j_engappai_2024_108228 crossref_primary_10_1016_j_neucom_2024_128418 crossref_primary_10_1016_j_engappai_2024_108033 crossref_primary_10_1109_TCYB_2025_3530951 crossref_primary_10_1016_j_swevo_2025_101913 crossref_primary_10_1016_j_neucom_2024_129156 crossref_primary_10_1016_j_neucom_2024_129311 crossref_primary_10_1016_j_neunet_2024_107025 crossref_primary_10_1109_JAS_2024_124989 crossref_primary_10_1016_j_neucom_2024_128185 crossref_primary_10_1109_TSMC_2025_3554219 crossref_primary_10_1007_s11071_024_10173_1 crossref_primary_10_1016_j_neucom_2025_130332 crossref_primary_10_3390_math12162499 crossref_primary_10_1109_TCSI_2024_3387914 crossref_primary_10_1109_TASE_2023_3313159 crossref_primary_10_1002_acs_3850 crossref_primary_10_1016_j_neucom_2023_127048 crossref_primary_10_1109_TII_2024_3488790 crossref_primary_10_1016_j_neucom_2025_129986 crossref_primary_10_1109_TSMC_2024_3428482 crossref_primary_10_1109_TASE_2024_3427657 crossref_primary_10_1109_TCDS_2024_3384269 crossref_primary_10_1016_j_automatica_2025_112168 crossref_primary_10_1016_j_neunet_2023_09_009 crossref_primary_10_1016_j_eswa_2024_123280 crossref_primary_10_1109_TCYB_2025_3562172 crossref_primary_10_1109_JAS_2024_125067 crossref_primary_10_1002_acs_3928 crossref_primary_10_1002_rnc_7595 crossref_primary_10_1016_j_neunet_2024_106347 crossref_primary_10_1109_TCSII_2024_3359258 crossref_primary_10_1016_j_neunet_2025_107280 crossref_primary_10_1109_TSMC_2024_3417230 crossref_primary_10_1080_00207721_2024_2312886 crossref_primary_10_1007_s11071_024_09524_9 crossref_primary_10_1109_TASE_2025_3539772 crossref_primary_10_1109_TNNLS_2025_3570716 crossref_primary_10_1109_TASE_2025_3581315 crossref_primary_10_1002_rnc_7183 crossref_primary_10_1016_j_neucom_2025_129977 crossref_primary_10_23919_cje_2024_00_287 crossref_primary_10_3389_frai_2024_1458230 crossref_primary_10_1016_j_neucom_2024_127592 crossref_primary_10_1016_j_neunet_2024_106274 crossref_primary_10_1109_TSMC_2024_3461781 crossref_primary_10_1109_TASE_2025_3567285 crossref_primary_10_1109_TCSII_2023_3339577 crossref_primary_10_1016_j_neucom_2023_127198 crossref_primary_10_1016_j_neunet_2025_107249 crossref_primary_10_1002_rnc_7583 crossref_primary_10_1002_rnc_7660 crossref_primary_10_1109_TFUZZ_2025_3581421 crossref_primary_10_1007_s11071_025_10946_2 crossref_primary_10_1109_TCSII_2023_3339829 crossref_primary_10_1002_acs_3793 crossref_primary_10_1109_TCSI_2024_3492255 crossref_primary_10_1016_j_neucom_2024_127835 crossref_primary_10_1016_j_engappai_2024_108284 crossref_primary_10_1016_j_neucom_2024_128734 crossref_primary_10_1016_j_neunet_2024_106483 crossref_primary_10_1002_rnc_7334 crossref_primary_10_1016_j_neunet_2024_106364
Cites_doi	10.1109/TAC.2019.2926167 10.1109/MCI.2019.2919363 10.1109/TSMC.2015.2417510 10.1109/TAC.2018.2790260 10.1109/TNNLS.2013.2281663 10.1109/TNNLS.2022.3178746 10.1109/JAS.2021.1003814 10.1109/TCYB.2021.3121542 10.1109/TCYB.2015.2492242 10.1109/TNNLS.2021.3123361 10.1038/nature16961 10.1109/72.623201 10.1109/TIE.2017.2698377 10.1109/JAS.2022.105692 10.1109/TSMCB.2008.926614 10.1109/TAC.2019.2905215 10.1016/j.epsr.2004.06.011 10.1109/TPWRS.2018.2823641 10.1109/72.914523 10.1109/TNNLS.2021.3051030 10.1109/TSMC.2017.2771516 10.1109/MCAS.2009.933854 10.1109/TNNLS.2022.3143527 10.1002/9780470182963 10.1109/TCYB.2021.3107801 10.1007/s10462-021-10118-9 10.1109/TNNLS.2022.3152268 10.1109/TNNLS.2020.2965208 10.1109/TSMC.2019.2898389 10.1109/TPWRS.2021.3100898 10.1109/TNNLS.2019.2919614 10.1109/TNN.2011.2168538 10.1016/j.neunet.2021.08.025 10.1109/TSMC.2021.3071968 10.1109/TAC.2021.3108121 10.1016/j.ins.2017.05.005
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D 2B. 4A8 92I 93N PSX TCJ
DOI	10.1109/JAS.2023.123684
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ)
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2329-9274
EndPage	1809
ExternalDocumentID	zdhxb_ywb202309002 10_1109_JAS_2023_123684 10219081
Genre	orig-research
GroupedDBID	-0I -0Y -SI -S~ 0R~ 4.4 5VR 6IK 92M 97E 9D9 9DI AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK AFUIB AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CAJEI EBS EJD IFIPE IPLJI JAVBF M43 O9- OCL PQQKQ Q-- RIA RIE RT9 T8Y TCJ TGT U1F U1G U5I U5S AAYXX CITATION 7SC 7SP 7TB 8FD FR3 JQ2 L7M L~C L~D 2B. 4A8 92I 93N PSX R-I RIG
ID	FETCH-LOGICAL-c325t-be0640a00965b1b1d923902213c0446d7267af8c9189b87f5fa40070f1d5d9ac3
IEDL.DBID	RIE
ISICitedReferencesCount	89
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001049972900002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2329-9266
IngestDate	Thu May 29 04:10:31 EDT 2025 Sun Nov 30 05:24:56 EST 2025 Sat Nov 29 03:31:08 EST 2025 Tue Nov 18 21:25:26 EST 2025 Wed Aug 27 02:14:21 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	9
Keywords	artificial neural networks Adaptive critic optimal control Hamilton-Jacobi-Bellman(HJB)equation multi-step heuristic dynamic pro-gramming multi-step reinforcement learning
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c325t-be0640a00965b1b1d923902213c0446d7267af8c9189b87f5fa40070f1d5d9ac3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
PQID	2851345375
PQPubID	2040495
PageCount	13
ParticipantIDs	crossref_primary_10_1109_JAS_2023_123684 wanfang_journals_zdhxb_ywb202309002 crossref_citationtrail_10_1109_JAS_2023_123684 ieee_primary_10219081 proquest_journals_2851345375
PublicationCentury	2000
PublicationDate	2023-09-01
PublicationDateYYYYMMDD	2023-09-01
PublicationDate_xml	– month: 09 year: 2023 text: 2023-09-01 day: 01
PublicationDecade	2020
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE/CAA journal of automatica sinica
PublicationTitleAbbrev	JAS
PublicationTitle_FL	IEEE/CAA Journal of Automatica Sinica
PublicationYear	2023
Publisher	Chinese Association of Automation (CAA) The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Faculty of Information Technology,the Beijing Key Laboratory of Computational Intelligence and Intelligent System,the Beijing Laboratory of Smart Environmental Protection,and the Beijing Institute of Artificial Intelligence,Beijing University of Technology,Beijing 100124,China
Publisher_xml	– name: Chinese Association of Automation (CAA) – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) – name: Faculty of Information Technology,the Beijing Key Laboratory of Computational Intelligence and Intelligent System,the Beijing Laboratory of Smart Environmental Protection,and the Beijing Institute of Artificial Intelligence,Beijing University of Technology,Beijing 100124,China
References	ref35 wang (ref25) 2020; 105 ref12 ref34 ref37 ref14 ref36 ref31 ref30 ref11 ref33 ref10 ref32 ref2 sutton (ref41) 1998 ref39 ref38 ref19 ref18 bertsekas (ref16) 1995; 1 ref24 ref23 ref26 ref20 silver (ref1) 2016; 529 mnih (ref22) 0; 48 ref21 ref43 werbos (ref15) 1992 ref28 powell (ref13) 2007 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 landelius (ref42) 1997 sutton (ref17) 1998
References_xml	– volume: 1 year: 1995 ident: ref16 publication-title: Dynamic Programming and Optimal Control Chapter – ident: ref28 doi: 10.1109/TAC.2019.2926167 – ident: ref2 doi: 10.1109/MCI.2019.2919363 – ident: ref32 doi: 10.1109/TSMC.2015.2417510 – ident: ref39 doi: 10.1109/TAC.2018.2790260 – year: 1998 ident: ref17 publication-title: Reinforcement Learning – ident: ref31 doi: 10.1109/TNNLS.2013.2281663 – ident: ref12 doi: 10.1109/TNNLS.2022.3178746 – ident: ref33 doi: 10.1109/JAS.2021.1003814 – volume: 48 start-page: 1928 year: 0 ident: ref22 article-title: Asynchronous methods for deep reinforcement learning publication-title: Proc Int Conf Machine Learning – ident: ref3 doi: 10.1109/TCYB.2021.3121542 – start-page: 163 year: 1998 ident: ref41 article-title: Eligibility traces publication-title: Reinforcement Learning An Introduction – ident: ref34 doi: 10.1109/TCYB.2015.2492242 – ident: ref10 doi: 10.1109/TNNLS.2021.3123361 – volume: 529 start-page: 484 year: 2016 ident: ref1 article-title: Mastering the game of go with deep neural networks and tree search publication-title: Nature doi: 10.1038/nature16961 – ident: ref14 doi: 10.1109/72.623201 – ident: ref4 doi: 10.1109/TIE.2017.2698377 – ident: ref8 doi: 10.1109/JAS.2022.105692 – ident: ref27 doi: 10.1109/TSMCB.2008.926614 – ident: ref11 doi: 10.1109/TAC.2019.2905215 – ident: ref43 doi: 10.1016/j.epsr.2004.06.011 – ident: ref5 doi: 10.1109/TPWRS.2018.2823641 – ident: ref18 doi: 10.1109/72.914523 – year: 1997 ident: ref42 article-title: Reinforcement learning and distributed local model synthesis publication-title: Linkoping Univ Linkoping – ident: ref9 doi: 10.1109/TNNLS.2021.3051030 – ident: ref21 doi: 10.1109/TSMC.2017.2771516 – ident: ref35 doi: 10.1109/MCAS.2009.933854 – ident: ref29 doi: 10.1109/TNNLS.2022.3143527 – year: 2007 ident: ref13 publication-title: Approximate Dynamic Programming Solving the Curses of Dimensionality doi: 10.1002/9780470182963 – ident: ref24 doi: 10.1109/TCYB.2021.3107801 – year: 1992 ident: ref15 article-title: Approximate dynamic programming for real-time control and neural modeling publication-title: Handbook of Intelligent Control Neural Fuzzy and Adaptive Approaches – volume: 105 start-page: 104443:1 year: 2020 ident: ref25 article-title: Adaptive-critic-based hybrid intelligent optimal tracking for a class of nonlinear discrete-time systems publication-title: Engineering Applications of Artificial Intelligence – ident: ref7 doi: 10.1007/s10462-021-10118-9 – ident: ref37 doi: 10.1109/TNNLS.2022.3152268 – ident: ref23 doi: 10.1109/TNNLS.2020.2965208 – ident: ref30 doi: 10.1109/TSMC.2019.2898389 – ident: ref6 doi: 10.1109/TPWRS.2021.3100898 – ident: ref19 doi: 10.1109/TNNLS.2019.2919614 – ident: ref36 doi: 10.1109/TNN.2011.2168538 – ident: ref38 doi: 10.1016/j.neunet.2021.08.025 – ident: ref40 doi: 10.1109/TSMC.2021.3071968 – ident: ref26 doi: 10.1109/TAC.2021.3108121 – ident: ref20 doi: 10.1016/j.ins.2017.05.005
SSID	ssj0001257694
Score	2.5390553
Snippet	This paper is concerned with a novel integrated multi-step heuristic dynamic programming (MsHDP) algorithm for solving optimal control problems. It is shown... This paper is concerned with a novel integrated multi-step heuristic dynamic programming(MsHDP)algorithm for solving optimal control problems.It is shown...
SourceID	wanfang proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1797
SubjectTerms	Adaptive control Adaptive critic Algorithms artificial neural networks Convergence Cost function Dynamic programming Hamilton-Jacobi-Bellman (HJB) equation Heuristic algorithms Iterative methods Mathematical models multi-step heuristic dynamic programming multi-step reinforcement learning Neural networks Observers Optimal control Policies Stability analysis Stability criteria Time optimal control
Title	Adaptive Multi-Step Evaluation Design With Stability Guarantee for Discrete-Time Optimal Learning Control
URI	https://ieeexplore.ieee.org/document/10219081 https://www.proquest.com/docview/2851345375 https://d.wanfangdata.com.cn/periodical/zdhxb-ywb202309002
Volume	10
WOSCitedRecordID	wos001049972900002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2329-9274 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001257694 issn: 2329-9266 databaseCode: RIE dateStart: 20140101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JS8QwGA0qCnpwF8eNgB68ZGyapmmOgwsiooKK3krWcUDr4IzrrzdfWnU8ePBWaJqWvDTfS77lIbQjNdOeJ54kmU5IxhQlRU4LIpxj3OUsS11ULTkVZ2fF7a28aJLVYy6Mcy4Gn7k2XEZfvn00z3BUtgcy1DKBROtxIfI6WWvkQCVQ5yh8GEiCJDJYnqaUD03k3knnsg1K4W2oNlJkv6xQlFX5xTCnXlXlVdUdMTVHc__8yHk023BK3KknwQIac9UimhmpNLiEeh2r-rCy4ZhxSyC4Cx9-V_rGBzGQA9_0hnc48M8YMfuOYf7AyDscqC0-6IUlJnBsAmkj-Dx09xDe2hRo7eL9Ouh9GV0fHV7tH5NGZYEYlvIh0Q6ceQr2MlxTTW2gfDJYdsoMOHutSHOhfGEkLaQuhOdegZZ64qnlVirDVtBE9Vi5VYTDapGanHmrFM_Ao-idtKLQqclszqloofbXqJemKUEOShj3ZdyKJLIMMJUAU1nD1EK73w_06-obfzddBixGmtUwtNDGF65l83sOyjTwTJZxJngLbTdY_9z9sHdvunx_1dB9IoPNWPuj83U0DW3qmLMNNDF8enabaNK8DHuDp604Pz8BTUDg6Q
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB5VLQg4QIEithSwBAcu3tpxnMTHVR9qYbsgUURvlp_tSpBW7fbFr8fjpGV76IFbpDhONJ_j-WzPzAfwUVlho2SRstIyWgrDaVPxhtYhCBkqURYhq5aM68mkOThQ3_pk9ZwLE0LIwWdhiJf5LN8fu3PcKltHGWrFMNF6SZZlwbp0rbktlUSes_RhogmKquR7-mI-nKn1z6PvQ9QKH2K9kaa844eysModjvnw0rTRtIdzzmb72X9-5jI87VklGXXD4DkshPYFPJmrNfgSpiNvTnBuIznnlmJ4F9m6rfVNNnMoB_k5nR2RxEBzzOw1wRGEtg8kkVuyOU2TTGLZFBNHyNfU3e_01r5E6yHZ6MLeV-DH9tb-xg7tdRaoE4WcURvwOM_gakZabrlPpE8l386Fw-NeXxdVbWLjFG-Ubeooo0E1dRa5l14ZJ17BYnvchtdA0nxRuEpEb0xCKBkhBuXrxhau9JXk9QCGN1bXri9CjloYv3RejDClE0waYdIdTAP4dPvASVd_4_6mK4jFXLMOhgGs3eCq-x_0TBeJaYpSiloO4EOP9b-7f_zRldXXlxa7Zyp5jdV7On8Pj3b298Z6vDv58gYeY_suAm0NFmen5-EtPHAXs-nZ6bs8Vv8CJpjkMA
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Adaptive+Multi-Step+Evaluation+Design+With+Stability+Guarantee+for+Discrete-Time+Optimal+Learning+Control&rft.jtitle=IEEE%2FCAA+journal+of+automatica+sinica&rft.au=Wang%2C+Ding&rft.au=Wang%2C+Jiangyu&rft.au=Zhao%2C+Mingming&rft.au=Xin%2C+Peng&rft.date=2023-09-01&rft.pub=Chinese+Association+of+Automation+%28CAA%29&rft.issn=2329-9266&rft.volume=10&rft.issue=9&rft.spage=1797&rft.epage=1809&rft_id=info:doi/10.1109%2FJAS.2023.123684&rft.externalDocID=10219081
thumbnail_s	http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fzdhxb-ywb%2Fzdhxb-ywb.jpg