Data‐driven policy iteration algorithm for continuous‐time stochastic linear‐quadratic optimal control problems

This paper studies a continuous‐time stochastic linear‐quadratic (SLQ) optimal control problem on infinite‐horizon. Combining the Kronecker product theory with an existing policy iteration algorithm, a data‐driven policy iteration algorithm is proposed to solve the problem. In contrast to most exist...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Asian journal of control Ročník 26; číslo 1; s. 481 - 489
Hlavní autoři: Zhang, Heng, Li, Na
Médium: Journal Article
Jazyk:angličtina
Vydáno: Hoboken Wiley Subscription Services, Inc 01.01.2024
Témata:
ISSN:1561-8625, 1934-6093
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract This paper studies a continuous‐time stochastic linear‐quadratic (SLQ) optimal control problem on infinite‐horizon. Combining the Kronecker product theory with an existing policy iteration algorithm, a data‐driven policy iteration algorithm is proposed to solve the problem. In contrast to most existing methods that need all information of system coefficients, the proposed algorithm eliminates the requirement of three system matrices by utilizing data of a stochastic system. More specifically, this algorithm uses the collected data to iteratively approximate the optimal control and a solution of the stochastic algebraic Riccati equation (SARE) corresponding to the SLQ optimal control problem. The convergence analysis of the obtained algorithm is given rigorously, and a simulation example is provided to illustrate the effectiveness and applicability of the algorithm.
AbstractList This paper studies a continuous‐time stochastic linear‐quadratic (SLQ) optimal control problem on infinite‐horizon. Combining the Kronecker product theory with an existing policy iteration algorithm, a data‐driven policy iteration algorithm is proposed to solve the problem. In contrast to most existing methods that need all information of system coefficients, the proposed algorithm eliminates the requirement of three system matrices by utilizing data of a stochastic system. More specifically, this algorithm uses the collected data to iteratively approximate the optimal control and a solution of the stochastic algebraic Riccati equation (SARE) corresponding to the SLQ optimal control problem. The convergence analysis of the obtained algorithm is given rigorously, and a simulation example is provided to illustrate the effectiveness and applicability of the algorithm.
Author Li, Na
Zhang, Heng
Author_xml – sequence: 1
  givenname: Heng
  orcidid: 0000-0003-2508-1137
  surname: Zhang
  fullname: Zhang, Heng
  organization: Shandong University
– sequence: 2
  givenname: Na
  surname: Li
  fullname: Li, Na
  email: naibor@163.com
  organization: Shandong University of Finance and Economics
BookMark eNp1kDtOAzEQhi0EEhAouIElKooNfqy96xKFt5AogHrlzHrBkbMOtheUjiNwRk6Ck1AhqGak-b4Zzb-PtnvfG4SOKBlTQtipjjMYc8b4FtqjipeFJIpv515IWtSSiV20H-OMEEl5LfbQcK6T_vr4bIN9Mz1eeGdhiW0yQSfre6zdsw82vcxx5wMG3yfbD36IWUl2bnBMHl50TBaws73RIQ9eB92udMB-kSHt1l7wDi-Cnzozjwdop9MumsOfOkJPlxePk-vi7v7qZnJ2VwDnjBdiymSlpqoWhteVAMVKokVdth20HGRNp13ZAdQCGGmVVryCTlZatqIiIFvFR-h4szcffh1MTM3MD6HPJxumKCUlr5XM1OmGguBjDKZrwKb1-ylo6xpKmlW2zSrbZpVtNk5-GYuQHw3LP9mf7e_WmeX_YHP2cDtZG9_Xt5GE
CitedBy_id crossref_primary_10_1016_j_ejcon_2025_101226
crossref_primary_10_1016_j_sysconle_2025_106050
Cites_doi 10.1016/j.neucom.2017.03.053
10.1109/9.788532
10.1109/TAC.2022.3181248
10.3934/math.2023519
10.1016/j.automatica.2006.09.019
10.1137/0306044
10.1016/j.automatica.2012.06.096
10.1109/TNNLS.2022.3209154
10.1002/asjc.2306
10.1137/15M103532X
10.1016/j.ins.2012.07.006
10.1007/s11432-020-3177-8
10.3934/jimo.2020030
10.1007/s11768-021-00046-y
10.1109/TASE.2022.3183610
10.1109/TII.2022.3168434
10.1080/00207179.2013.790562
10.1007/s00245-017-9402-8
10.1016/j.automatica.2022.110561
10.1109/TNNLS.2020.3042120
10.1002/asjc.61
10.1109/9.863597
10.1007/978-1-4612-1466-3
10.1109/TCYB.2021.3070352
10.1002/asjc.406
10.1016/j.automatica.2011.03.005
10.1016/j.sysconle.2009.11.006
10.1016/j.automatica.2008.08.017
10.1109/TIE.2021.3076729
10.1109/ACC.1994.735224
ContentType Journal Article
Copyright 2023 Chinese Automatic Control Society and John Wiley & Sons Australia, Ltd
2024 Chinese Automatic Control Society and John Wiley & Sons Australia, Ltd
Copyright_xml – notice: 2023 Chinese Automatic Control Society and John Wiley & Sons Australia, Ltd
– notice: 2024 Chinese Automatic Control Society and John Wiley & Sons Australia, Ltd
DBID AAYXX
CITATION
JQ2
DOI 10.1002/asjc.3223
DatabaseName CrossRef
ProQuest Computer Science Collection
DatabaseTitle CrossRef
ProQuest Computer Science Collection
DatabaseTitleList ProQuest Computer Science Collection
CrossRef

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1934-6093
EndPage 489
ExternalDocumentID 10_1002_asjc_3223
ASJC3223
Genre article
GrantInformation_xml – fundername: National Natural Science Foundation of China
  funderid: 61821004; 61925306; 12171279; 11801317
– fundername: Colleges and Universities Youth Innovation Technology Program of Shandong Province
  funderid: 2019KJI011
– fundername: Natural Science Foundation of Shandong Province
  funderid: ZR2020ZD24; ZR2019MA013
– fundername: National Key R&D Program of China
  funderid: 2022YFA1006103
GroupedDBID .4S
.DC
05W
0R~
1L6
1OC
23N
31~
33P
3SF
4.4
52U
5DZ
5GY
8-0
8-1
A00
AAESR
AAEVG
AAHHS
AAHQN
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCUV
ABJNI
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACGFS
ACIWK
ACPOU
ACRPL
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADNMO
ADOZA
ADXAS
ADZMN
ADZOD
AEEZP
AEIGN
AEIMD
AENEX
AEQDE
AEUQT
AEUYR
AFBPY
AFFPM
AFGKR
AFPWT
AFWVQ
AHBTC
AITYG
AIURR
AIWBW
AJBDE
AJXKR
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ARCSS
ASPBG
ATUGU
AUFTA
AVWKF
AZFZN
AZVAB
BDRZF
BFHJK
BHBCM
BMNLL
BMXJE
BNHUX
BOGZA
BRXPI
CS3
DCZOG
DRFUL
DRSTM
EBS
EJD
F5P
FEDTE
G-S
GODZA
HGLYW
HVGLF
HZ~
I-F
J9A
LATKE
LEEKS
LH4
LITHE
LOXES
LUTES
LW6
LYRES
MEWTI
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
MY.
MY~
O9-
OIG
P2W
P4E
PQQKQ
ROL
RWI
SUPJJ
TUS
WBKPD
WIH
WIK
WOHZO
WXSBR
WYJ
XV2
ZZTAW
~S-
AAMMB
AAYXX
ADMLS
AEFGJ
AEYWJ
AGHNM
AGQPQ
AGXDD
AGYGG
AIDQK
AIDYY
CITATION
JQ2
ID FETCH-LOGICAL-c3323-5b2679b985e3875c9240a584dfcd3c681bf4fcc85c20d9a937cf67a6d570c6d93
IEDL.DBID DRFUL
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001058857600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1561-8625
IngestDate Fri Jul 25 10:39:49 EDT 2025
Sat Nov 29 04:00:07 EST 2025
Tue Nov 18 21:56:35 EST 2025
Wed Jan 22 16:15:18 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3323-5b2679b985e3875c9240a584dfcd3c681bf4fcc85c20d9a937cf67a6d570c6d93
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-2508-1137
OpenAccessLink https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/asjc.3223
PQID 2911043896
PQPubID 866359
PageCount 9
ParticipantIDs proquest_journals_2911043896
crossref_citationtrail_10_1002_asjc_3223
crossref_primary_10_1002_asjc_3223
wiley_primary_10_1002_asjc_3223_ASJC3223
PublicationCentury 2000
PublicationDate January 2024
2024-01-00
20240101
PublicationDateYYYYMMDD 2024-01-01
PublicationDate_xml – month: 01
  year: 2024
  text: January 2024
PublicationDecade 2020
PublicationPlace Hoboken
PublicationPlace_xml – name: Hoboken
PublicationTitle Asian journal of control
PublicationYear 2024
Publisher Wiley Subscription Services, Inc
Publisher_xml – name: Wiley Subscription Services, Inc
References 2009; 45
2010; 59
2021; 23
2000; 45
1960; 5
2023; 8
2013; 86
2023; 19
1968; 6
2016; 54
2020; 369
2022; 67
1974
1999; 44
2022; 69
2008; 10
1994
2013; 220
1992
2022; 65
2012; 14
1999
2023; 20
2022; 145
2023; 68
2022
2018; 339
2021; 17
2021; 19
2018
2022; 52
2012; 48
2022; 33
2011; 47
2018; 78
2007; 43
2017; 247
e_1_2_9_30_1
e_1_2_9_31_1
e_1_2_9_34_1
e_1_2_9_35_1
e_1_2_9_13_1
e_1_2_9_32_1
e_1_2_9_12_1
e_1_2_9_33_1
Sutton R. S. (e_1_2_9_15_1) 2018
e_1_2_9_38_1
e_1_2_9_17_1
e_1_2_9_16_1
e_1_2_9_37_1
e_1_2_9_19_1
Zhang H. (e_1_2_9_10_1) 2020; 369
Wu A. (e_1_2_9_11_1) 2018; 339
e_1_2_9_18_1
e_1_2_9_20_1
e_1_2_9_22_1
e_1_2_9_21_1
e_1_2_9_24_1
e_1_2_9_23_1
e_1_2_9_8_1
e_1_2_9_7_1
e_1_2_9_6_1
e_1_2_9_5_1
e_1_2_9_4_1
e_1_2_9_3_1
Werbos P. J. (e_1_2_9_14_1) 1974
e_1_2_9_9_1
e_1_2_9_26_1
e_1_2_9_25_1
e_1_2_9_28_1
Kalman R. E. (e_1_2_9_2_1) 1960; 5
e_1_2_9_27_1
e_1_2_9_29_1
Peng C. (e_1_2_9_36_1) 2023; 68
References_xml – volume: 48
  start-page: 2699
  year: 2012
  end-page: 2704
  article-title: Computational adaptive optimal control for continuous‐time linear systems with completely unknown dynamics
  publication-title: Automatica
– volume: 86
  start-page: 1554
  year: 2013
  end-page: 1566
  article-title: Neural‐network‐observer‐based optimal control for unknown nonlinear systems using adaptive dynamic programming
  publication-title: Internat. J. Control
– volume: 69
  start-page: 4022
  year: 2022
  end-page: 4033
  article-title: Dual‐loop tube‐based robust model predictive attitude tracking control for spacecraft with system constraints and additive disturbances
  publication-title: IEEE Trans. Ind. Electron.
– volume: 23
  start-page: 979
  year: 2021
  end-page: 989
  article-title: Discrete‐time mean‐field stochastic linear‐quadratic optimal control problem with finite horizon
  publication-title: Asian J. Control
– volume: 52
  start-page: 11805
  year: 2022
  end-page: 11818
  article-title: Indefinite mean‐field stochastic cooperative linear‐quadratic dynamic difference game with its application to the network security model
  publication-title: IEEE Trans. Cybern.
– volume: 33
  start-page: 1400
  year: 2022
  end-page: 1413
  article-title: Design and implementation of deep neural network‐based control for automatic parking maneuver process
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 6
  start-page: 681
  year: 1968
  end-page: 697
  article-title: On a matrix Riccati equation of stochastic control
  publication-title: SIAM J. Control
– volume: 59
  start-page: 50
  year: 2010
  end-page: 56
  article-title: An iterative algorithm to solve state‐perturbed stochastic algebraic Riccati equations in LQ zero‐sum games
  publication-title: Syst. Control Lett.
– volume: 44
  start-page: 1653
  year: 1999
  end-page: 1662
  article-title: Adaptive continuous‐time linear quadratic Gaussian control
  publication-title: IEEE Trans. Automat. Control
– volume: 65
  start-page: 172203
  year: 2022
  article-title: Multicriteria optimization problems of finite horizon stochastic cooperative linear‐quadratic difference games
  publication-title: Sci. China Inf. Sci.
– volume: 339
  start-page: 410
  year: 2018
  end-page: 421
  article-title: Two iterative algorithms for stochastic algebraic Riccati matrix equations
  publication-title: Appl. Math. Comput.
– volume: 67
  start-page: 5009
  year: 2022
  end-page: 5016
  article-title: Stochastic linear quadratic optimal control problem: a reinforcement learning method
  publication-title: IEEE Trans. Automat. Control
– volume: 10
  start-page: 608
  year: 2008
  end-page: 615
  article-title: Infinite horizon linear quadratic optimal control for discrete‐time stochastic systems
  publication-title: Asian J. Control
– volume: 19
  start-page: 74
  year: 2023
  end-page: 87
  article-title: Multi‐phase overtaking maneuver planning for autonomous ground vehicles via a desensitized trajectory optimization approach
  publication-title: IEEE Trans. Ind. Informat.
– volume: 68
  start-page: 4113
  year: 2023
  end-page: 4126
  article-title: Pareto optimality in infinite horizon mean‐field stochastic cooperative linear‐quadratic difference games
  publication-title: IEEE Trans. Automat. Control
– volume: 78
  start-page: 145
  year: 2018
  end-page: 183
  article-title: Stochastic linear quadratic optimal control problems in infinite horizon
  publication-title: Appl. Math. Optim.
– volume: 220
  start-page: 331
  year: 2013
  end-page: 342
  article-title: An iterative adaptive dynamic programming algorithm for optimal control of unknown discrete‐time nonlinear systems with constrained inputs
  publication-title: Info. Sci.
– year: 2018
– start-page: 295
  year: 1992
  end-page: 302
– volume: 247
  start-page: 192
  year: 2017
  end-page: 201
  article-title: Data‐based adaptive neural network optimal output feedback control for nonlinear systems with actuator saturation
  publication-title: Neurocomputing
– volume: 45
  start-page: 477
  year: 2009
  end-page: 484
  article-title: Adaptive optimal control for continuous‐time linear systems based on policy iteration
  publication-title: Automatica
– volume: 19
  start-page: 315
  year: 2021
  end-page: 327
  article-title: Neural‐network‐based stochastic linear quadratic optimal tracking control scheme for unknown discrete‐time systems using adaptive dynamic programming
  publication-title: Control Theory Technol.
– volume: 54
  start-page: 2274
  year: 2016
  end-page: 2308
  article-title: Open‐loop and closed‐loop solvabilities for stochastic linear quadratic optimal control problems
  publication-title: SIAM J. Control Optim.
– volume: 17
  start-page: 1471
  year: 2021
  end-page: 1488
  article-title: Finite‐horizon optimal control of discrete‐time linear systems with completely unknown dynamics using Q‐learning
  publication-title: J. Ind. Manage. Optim.
– volume: 45
  start-page: 1131
  year: 2000
  end-page: 1143
  article-title: Linear matrix inequalities, Riccati equations, and indefinite stochastic linear quadratic controls
  publication-title: IEEE Trans. Automat. Control
– volume: 47
  start-page: 1556
  year: 2011
  end-page: 1569
  article-title: Multi‐player non‐zero‐sum games: online adaptive learning solution of coupled Hamilton‐Jacobi‐equations
  publication-title: Automatica
– year: 2022
– volume: 369
  start-page: 1
  year: 2020
  end-page: 11
  article-title: Backward stochastic optimal control with mixed deterministic controller and random controller and its applications in linear‐quadratic control
  publication-title: Appl. Math. Comput.
– volume: 145
  start-page: 110561
  year: 2022
  article-title: Attitude tracking control for reentry vehicles using centralized robust model predictive control
  publication-title: Automatica
– volume: 20
  start-page: 1633
  year: 2023
  end-page: 1647
  article-title: Deep learning‐based trajectory planning and control for autonomous ground vehicle parking maneuver
  publication-title: IEEE Trans. Automat. Sci. Eng.
– year: 1974
– volume: 8
  start-page: 10249
  year: 2023
  end-page: 10265
  article-title: Stochastic linear quadratic optimal tracking control for discrete‐time systems with delays based on Q‐learning algorithm
  publication-title: AIMS Math.
– volume: 43
  start-page: 473
  year: 2007
  end-page: 481
  article-title: Model‐free Q‐learning designs for linear discrete‐time zero‐sum games with application to H‐infinity control
  publication-title: Automatica
– start-page: 3475
  year: 1994
  end-page: 3479
– volume: 5
  start-page: 102
  year: 1960
  end-page: 119
  article-title: Contributions to the theory of optimal control
  publication-title: Bol. Soc. Mat. Mex.
– volume: 14
  start-page: 173
  year: 2012
  end-page: 185
  article-title: Linear‐quadratic optimal control and nonzero‐sum differential game of forward‐backward stochastic system
  publication-title: Asian J. Control
– year: 1999
– ident: e_1_2_9_22_1
  doi: 10.1016/j.neucom.2017.03.053
– ident: e_1_2_9_28_1
  doi: 10.1109/9.788532
– ident: e_1_2_9_29_1
  doi: 10.1109/TAC.2022.3181248
– volume: 339
  start-page: 410
  year: 2018
  ident: e_1_2_9_11_1
  article-title: Two iterative algorithms for stochastic algebraic Riccati matrix equations
  publication-title: Appl. Math. Comput.
– ident: e_1_2_9_27_1
  doi: 10.3934/math.2023519
– ident: e_1_2_9_31_1
– ident: e_1_2_9_17_1
  doi: 10.1016/j.automatica.2006.09.019
– ident: e_1_2_9_3_1
  doi: 10.1137/0306044
– ident: e_1_2_9_20_1
  doi: 10.1016/j.automatica.2012.06.096
– ident: e_1_2_9_23_1
  doi: 10.1109/TNNLS.2022.3209154
– ident: e_1_2_9_9_1
  doi: 10.1002/asjc.2306
– ident: e_1_2_9_6_1
  doi: 10.1137/15M103532X
– ident: e_1_2_9_18_1
  doi: 10.1016/j.ins.2012.07.006
– ident: e_1_2_9_34_1
  doi: 10.1007/s11432-020-3177-8
– ident: e_1_2_9_16_1
  doi: 10.3934/jimo.2020030
– volume: 369
  start-page: 1
  year: 2020
  ident: e_1_2_9_10_1
  article-title: Backward stochastic optimal control with mixed deterministic controller and random controller and its applications in linear‐quadratic control
  publication-title: Appl. Math. Comput.
– ident: e_1_2_9_26_1
  doi: 10.1007/s11768-021-00046-y
– ident: e_1_2_9_25_1
  doi: 10.1109/TASE.2022.3183610
– ident: e_1_2_9_37_1
  doi: 10.1109/TII.2022.3168434
– ident: e_1_2_9_21_1
  doi: 10.1080/00207179.2013.790562
– ident: e_1_2_9_7_1
  doi: 10.1007/s00245-017-9402-8
– volume-title: Reinforcement learning: an introduction
  year: 2018
  ident: e_1_2_9_15_1
– ident: e_1_2_9_33_1
  doi: 10.1016/j.automatica.2022.110561
– ident: e_1_2_9_24_1
  doi: 10.1109/TNNLS.2020.3042120
– volume-title: Beyond regression: new tools for prediction and analysis in the behavioural sciences
  year: 1974
  ident: e_1_2_9_14_1
– ident: e_1_2_9_5_1
  doi: 10.1002/asjc.61
– volume: 68
  start-page: 4113
  year: 2023
  ident: e_1_2_9_36_1
  article-title: Pareto optimality in infinite horizon mean‐field stochastic cooperative linear‐quadratic difference games
  publication-title: IEEE Trans. Automat. Control
– ident: e_1_2_9_13_1
  doi: 10.1109/9.863597
– ident: e_1_2_9_4_1
  doi: 10.1007/978-1-4612-1466-3
– ident: e_1_2_9_35_1
  doi: 10.1109/TCYB.2021.3070352
– ident: e_1_2_9_8_1
  doi: 10.1002/asjc.406
– volume: 5
  start-page: 102
  year: 1960
  ident: e_1_2_9_2_1
  article-title: Contributions to the theory of optimal control
  publication-title: Bol. Soc. Mat. Mex.
– ident: e_1_2_9_32_1
  doi: 10.1016/j.automatica.2011.03.005
– ident: e_1_2_9_12_1
  doi: 10.1016/j.sysconle.2009.11.006
– ident: e_1_2_9_19_1
  doi: 10.1016/j.automatica.2008.08.017
– ident: e_1_2_9_38_1
  doi: 10.1109/TIE.2021.3076729
– ident: e_1_2_9_30_1
  doi: 10.1109/ACC.1994.735224
SSID ssj0061385
Score 2.3559666
Snippet This paper studies a continuous‐time stochastic linear‐quadratic (SLQ) optimal control problem on infinite‐horizon. Combining the Kronecker product theory with...
SourceID proquest
crossref
wiley
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 481
SubjectTerms Data collection
data‐driven
Iterative algorithms
Optimal control
policy iteration
Riccati equation
stochastic algebraic Riccati equation
stochastic linear‐quadratic optimal control problem
Stochastic systems
Title Data‐driven policy iteration algorithm for continuous‐time stochastic linear‐quadratic optimal control problems
URI https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fasjc.3223
https://www.proquest.com/docview/2911043896
Volume 26
WOSCitedRecordID wos001058857600001&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: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1934-6093
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0061385
  issn: 1561-8625
  databaseCode: DRFUL
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEA7aetCDb7G-COLBy9o0230ET0UtIqWIWvC2ZCcbW9G27nY9-xP8jf4SJ_uoFRQEbws72Q2ZzMw3eXxDyFFDRQzcyLYEA201Pda0QnB9C7Ep8zUDwdzsonDH63b9-3txPUdOy7swOT_EdMHNWEbmr42ByzCpf5GGyuQRTnA62vOkyj1m9mir5zftXqd0xBiosoqcmKE0LATuTkksxHh92vh7OPrCmLNINQs17ZV_dXKVLBcIk7byKbFG5qLhOlma4R3cIOm5nMiPt3cVG19Hxxk3MM0JllFPVD49jOLBpP9MEdJSc5p9MExHaYJNTC16ioAR-tIwPFPTRRnji5dUKtMc6Ai90DP2oDgFT4uaNckm6bUv7s4uraL-ggW2zW3LCbnriVD4TmRjWgOYqjGJgEVpUDYqtBHqpgbwHeBMCYlAB7TrSVc5HupfCXuLVIajYbRNKOI03RDK0xLhZuQ7UuomZipcaAEKRWvkuFRDAAU5uamR8RTktMo8MCMZmJGskcOp6Dhn5PhJaK_UZVAYZRJwdOxm41O4-LtMa79_IGjdXp2Zh52_i-6SRY6QJ1-g2SOVSZxG-2QBXieDJD4oZucn6rbvGg
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3JTsMwEB2xScCBHVFWC3HgEnCTZrHEBQEVS6kQi8QtcscxFEFbkoYzn8A38iWMsxSQQELiFinjxPKMx2_G9huAraqKOHqRYwmO2qr5vGa10AsswqY80BwF97KLwg2_2Qxub8XFEOyVd2FyfohBws3MjMxfmwluEtK7n6yhMnnAHbJHZxhGDe0VhV6jh5f1m0bpiWmlykpyUohStQi5uyWzELd3B42_r0efIPMrVM3Wmvr0_3o5A1MFxmT7uVHMwlDUmYPJL8yD85Aeyr58f31TsfF2rJexA7OcYpk0xeTjXTdu9--fGIFaZs6ztztpN02oialGzwgy4r00HM_M9FHG9OI5lco0R9YlP_REPSjOwbOiak2yADf1o-uDY6uowGCh49iO5bZszxctEbiRQ4ENUrDGJUEWpVE5pNJqS9c0YuCizZWQBHVQe770lOuTBSjhLMJIp9uJloARUtNVoXwtCXBGgSulrlGsYgstUJFoBbZLPYRY0JObKhmPYU6sbIdmJEMzkhXYHIj2ck6On4RWS2WGxbRMQptcu9n6FB79LlPb7x8I969OD8zD8t9FN2D8-Pq8ETZOmmcrMGETAMrTNasw0o_TaA3G8KXfTuL1wlQ_ACgP8wo
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSyNBEC58IXrwsSo-ojbiYS-z6cy7wYskBncNQXYVvA2d6mmNaBJnMp79Cf5Gf4nV84guKAjeBqZqpumqrv6qH18BHDZUzNGPHUtw1JYbcNfqoR9ahE15qDkK7ucXhTtBtxteXYnzKTiq7sIU_BCTBTczMvJ4bQZ4PFK6_sYaKtNb_EX-6EzDrOsJl7x8tvW3fdmpIjHNVHlJTkpRGhYhd69iFuJ2faL8_3z0BjLfQ9V8rmkvf6-VK7BUYkx2XDjFKkzFgx-w-I55cA2ylhzLl6dnlZhox0Y5OzArKJbJUkzeXQ-T_vjmnhGoZeY8e3-QDbOUVEw1ekaQEW-k4Xhmpo0yoRcPmVRGHdmQ4tA9taA8B8_KqjXpOly2Ty6ap1ZZgcFCx7Edy-vZfiB6IvRihxIbpGSNS4IsSqNyyKSNnnY1YuihzZWQBHVQ-4H0lReQByjhbMDMYDiIN4ERUtMNoQItCXDGoSeldilXsYUWqEh0C35WdoiwpCc3VTLuooJY2Y5MT0amJ7fgYCI6Kjg5PhKqVcaMymGZRjaFdrP1KXz6XW62zz8QHf_70zQP218X3Yf581Y76vzunu3Agk34p1itqcHMOMniXZjDx3E_TfZKT30FyVryhQ
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=Data%E2%80%90driven+policy+iteration+algorithm+for+continuous%E2%80%90time+stochastic+linear%E2%80%90quadratic+optimal+control+problems&rft.jtitle=Asian+journal+of+control&rft.au=Zhang%2C+Heng&rft.au=Li%2C+Na&rft.date=2024-01-01&rft.pub=Wiley+Subscription+Services%2C+Inc&rft.issn=1561-8625&rft.eissn=1934-6093&rft.volume=26&rft.issue=1&rft.spage=481&rft.epage=489&rft_id=info:doi/10.1002%2Fasjc.3223&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1561-8625&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1561-8625&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1561-8625&client=summon