Learning Adaptive Differential Evolution Algorithm From Optimization Experiences by Policy Gradient

Differential evolution is one of the most prestigious population-based stochastic optimization algorithm for black-box problems. The performance of a differential evolution algorithm depends highly on its mutation and crossover strategy and associated control parameters. However, the determination p...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on evolutionary computation Ročník 25; číslo 4; s. 666 - 680
Hlavní autoři:	Sun, Jianyong, Liu, Xin, Back, Thomas, Xu, Zongben
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.08.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Adaptive algorithms Adaptive control Adaptive differential evolution Algorithms Convergence Deep learning Evolutionary algorithms Evolutionary computation global optimization Machine learning Markov processes Mutation Optimization policy gradient (PG) Process control Process parameters Reinforcement learning reinforcement learning (RL) Sociology Statistics
ISSN:	1089-778X, 1941-0026
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Differential evolution is one of the most prestigious population-based stochastic optimization algorithm for black-box problems. The performance of a differential evolution algorithm depends highly on its mutation and crossover strategy and associated control parameters. However, the determination process for the most suitable parameter setting is troublesome and time consuming. Adaptive control parameter methods that can adapt to problem landscape and optimization environment are more preferable than fixed parameter settings. This article proposes a novel adaptive parameter control approach based on learning from the optimization experiences over a set of problems. In the approach, the parameter control is modeled as a finite-horizon Markov decision process. A reinforcement learning algorithm, named policy gradient, is applied to learn an agent (i.e., parameter controller) that can provide the control parameters of a proposed differential evolution adaptively during the search procedure. The differential evolution algorithm based on the learned agent is compared against nine well-known evolutionary algorithms on the CEC'13 and CEC'17 test suites. Experimental results show that the proposed algorithm performs competitively against these compared algorithms on the test suites.
AbstractList	Differential evolution is one of the most prestigious population-based stochastic optimization algorithm for black-box problems. The performance of a differential evolution algorithm depends highly on its mutation and crossover strategy and associated control parameters. However, the determination process for the most suitable parameter setting is troublesome and time consuming. Adaptive control parameter methods that can adapt to problem landscape and optimization environment are more preferable than fixed parameter settings. This article proposes a novel adaptive parameter control approach based on learning from the optimization experiences over a set of problems. In the approach, the parameter control is modeled as a finite-horizon Markov decision process. A reinforcement learning algorithm, named policy gradient, is applied to learn an agent (i.e., parameter controller) that can provide the control parameters of a proposed differential evolution adaptively during the search procedure. The differential evolution algorithm based on the learned agent is compared against nine well-known evolutionary algorithms on the CEC’13 and CEC’17 test suites. Experimental results show that the proposed algorithm performs competitively against these compared algorithms on the test suites.
Author	Back, Thomas Xu, Zongben Liu, Xin Sun, Jianyong
Author_xml	– sequence: 1 givenname: Jianyong orcidid: 0000-0002-9188-1856 surname: Sun fullname: Sun, Jianyong email: jy.sun@xjtu.edu.cn organization: School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China – sequence: 2 givenname: Xin orcidid: 0000-0003-4710-2103 surname: Liu fullname: Liu, Xin email: liuxin17@stu.xjtu.edu.cn organization: School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China – sequence: 3 givenname: Thomas orcidid: 0000-0001-6768-1478 surname: Back fullname: Back, Thomas email: t.h.w.baeck@liacs.leidenuniv.nl organization: Leiden Institute of Advanced Computer Science, Leiden University, Leiden, RA, The Netherlands – sequence: 4 givenname: Zongben surname: Xu fullname: Xu, Zongben email: zbxu@mail.xjtu.edu.cn organization: School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China
BookMark	eNp9kE1PAjEQhhuDiYD-AOOliefFtrS79EgQ0IQED2i8bbrtFEuWLXYLEX-9y0c8ePDUSed5ZzJPB7UqXwFCt5T0KCXyYTF-G_UYYbTXJykZUHqB2lRymhDC0lZTk4FMsmzwfoU6db0ihHJBZRvpGahQuWqJh0ZtotsBfnTWQoAqOlXi8c6X2-h8hYfl0gcXP9Z4Evwazxt47b7VsTf-2kBwUGmocbHHL750eo-nQZnmM16jS6vKGm7Obxe9TsaL0VMym0-fR8NZojlhMVGgDGGZUlIay4UtLEs5GCO1hUIVkksOQkORNghTWWZAWSus1BoEmMz0u-j-NHcT_OcW6piv_DZUzcqcCZHyQUq5bKjsROng6zqAzbWLxzNiUK7MKckPRvOD0fxgND8bbZL0T3IT3FqF_b-Zu1PGAcAvL_tCpoL1fwDitYds
CODEN	ITEVF5
CitedBy_id	crossref_primary_10_1016_j_engappai_2023_107017 crossref_primary_10_3390_a17110500 crossref_primary_10_1016_j_engappai_2023_107498 crossref_primary_10_1080_09540091_2025_2523960 crossref_primary_10_1109_ACCESS_2024_3440885 crossref_primary_10_1088_1361_6501_ac50e7 crossref_primary_10_1016_j_ins_2021_11_043 crossref_primary_10_1016_j_eswa_2023_119672 crossref_primary_10_1016_j_swevo_2024_101838 crossref_primary_10_1109_TEVC_2022_3219238 crossref_primary_10_1109_TETCI_2022_3146882 crossref_primary_10_1016_j_swevo_2024_101517 crossref_primary_10_3390_electronics12224639 crossref_primary_10_1109_TETCI_2024_3367809 crossref_primary_10_2478_amns_2024_1452 crossref_primary_10_1109_TSMC_2024_3488205 crossref_primary_10_1016_j_ins_2022_07_108 crossref_primary_10_1016_j_eswa_2023_120261 crossref_primary_10_1016_j_compag_2024_108845 crossref_primary_10_1016_j_ins_2022_10_111 crossref_primary_10_1016_j_swevo_2025_102125 crossref_primary_10_1016_j_eswa_2025_128913 crossref_primary_10_1016_j_knosys_2023_110801 crossref_primary_10_1016_j_eswa_2024_125105 crossref_primary_10_1109_TETCI_2025_3540405 crossref_primary_10_1155_2022_4481296 crossref_primary_10_1016_j_asoc_2025_113280 crossref_primary_10_1016_j_swevo_2023_101294 crossref_primary_10_1007_s10489_024_05906_z crossref_primary_10_1007_s41965_024_00172_x crossref_primary_10_1109_TCYB_2025_3561518 crossref_primary_10_1109_TCAD_2022_3149720 crossref_primary_10_1109_TETCI_2022_3210927 crossref_primary_10_1109_TII_2022_3218645 crossref_primary_10_26599_TST_2024_9010185 crossref_primary_10_1007_s40747_024_01620_y crossref_primary_10_1007_s11425_023_2252_9 crossref_primary_10_1016_j_swevo_2024_101627 crossref_primary_10_1016_j_swevo_2025_101844 crossref_primary_10_1016_j_asoc_2024_112605 crossref_primary_10_1016_j_ins_2024_120411 crossref_primary_10_1016_j_swevo_2022_101142 crossref_primary_10_1016_j_dwt_2024_100714 crossref_primary_10_1016_j_knosys_2022_110073 crossref_primary_10_1109_TSMC_2024_3374889 crossref_primary_10_1007_s10489_023_05180_5 crossref_primary_10_1016_j_eswa_2025_129538 crossref_primary_10_1016_j_eswa_2024_124646 crossref_primary_10_1007_s40747_022_00650_8 crossref_primary_10_1016_j_ins_2022_11_029 crossref_primary_10_1016_j_neucom_2023_126899 crossref_primary_10_1109_TEVC_2023_3250350 crossref_primary_10_1016_j_eswa_2023_121218 crossref_primary_10_1016_j_neucom_2025_130633 crossref_primary_10_1016_j_swevo_2025_101930 crossref_primary_10_1109_TETCI_2023_3251441 crossref_primary_10_1007_s10489_025_06687_9 crossref_primary_10_1109_TAES_2023_3312626 crossref_primary_10_1016_j_swevo_2025_102081 crossref_primary_10_1177_10996362241305836 crossref_primary_10_1109_TFUZZ_2025_3545442 crossref_primary_10_1007_s11425_023_2290_y crossref_primary_10_1016_j_swevo_2025_101866 crossref_primary_10_1016_j_swevo_2023_101387 crossref_primary_10_1016_j_swevo_2024_101644 crossref_primary_10_1016_j_eswa_2023_122674 crossref_primary_10_1016_j_swevo_2025_102038 crossref_primary_10_1016_j_engappai_2024_108081 crossref_primary_10_1016_j_swevo_2024_101486 crossref_primary_10_1016_j_eswa_2023_122076 crossref_primary_10_1016_j_swevo_2024_101521
Cites_doi	10.1109/CEC.2005.1554904 10.1109/4235.771166 10.1162/EVCO_a_00009 10.1109/TEVC.2008.927706 10.1109/CEC.2005.1554725 10.1109/TEVC.2009.2014613 10.1038/nature16961 10.1145/3319619.3326747 10.1145/1830483.1830490 10.1016/j.neucom.2013.04.036 10.1016/j.knosys.2019.01.006 10.1109/CEC.2018.8477908 10.1145/3319619.3326751 10.1145/1068009.1068177 10.1109/CEC.2019.8789904 10.1109/TEVC.2014.2308294 10.1109/CEC.2014.6900380 10.1016/j.knosys.2017.11.015 10.1109/TEVC.2010.2087271 10.1016/j.asoc.2009.02.010 10.1109/CEC.2013.6557555 10.1162/106365603321828970 10.1007/BF02551274 10.1007/s10462-015-9452-8 10.1016/j.asoc.2014.01.038 10.1145/3321707.3321813 10.1016/j.ejor.2015.10.043 10.1109/CEC.2017.7969307 10.1109/SITIS.2010.22 10.1109/TEVC.2010.2059031 10.1109/ICACTE.2010.5579677 10.1109/CEC.2016.7743922 10.1145/2598394.2605681 10.1007/s10462-009-9137-2 10.1023/A:1008202821328 10.1016/S0305-0548(03)00116-3 10.1109/TEVC.2014.2360890 10.1109/TCYB.2019.2892735 10.1023/A:1022995128597 10.1016/j.swevo.2016.01.004 10.1145/2576768.2598360 10.1007/s10589-007-9014-3 10.1109/CEC.2017.7969336 10.1016/j.asoc.2014.11.003 10.1109/TEVC.2006.872133 10.1162/neco.1997.9.8.1735 10.1109/CEC.2017.7969456
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TEVC.2021.3060811
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Statistics Computer Science
EISSN	1941-0026
EndPage	680
ExternalDocumentID	10_1109_TEVC_2021_3060811 9359652
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 11991023; 62076197 funderid: 10.13039/501100001809 – fundername: Major Project of National Science Foundation of China grantid: U1811461 funderid: 10.13039/501100001809 – fundername: Project of National Science Foundation of China grantid: 61721002 funderid: 10.13039/501100001809 – fundername: Key Project of National Science Foundation of China grantid: 11690011 funderid: 10.13039/501100001809
GroupedDBID	-~X .DC 0R~ 29I 4.4 5GY 5VS 6IF 6IK 6IL 6IN 97E AAJGR AARMG AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG ACGFO ACGFS ACIWK ADZIZ AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CHZPO CS3 EBS EJD HZ~ H~9 IEGSK IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RIL RNS TN5 VH1 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c402t-aead027aa99df45fbf264edd9cfebab9494e5ceb67aa2a77deaff5f9cce5ed7d3
IEDL.DBID	RIE
ISICitedReferencesCount	102
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000679530900008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1089-778X
IngestDate	Mon Jun 30 06:16:05 EDT 2025 Tue Nov 18 22:26:22 EST 2025 Sat Nov 29 03:13:48 EST 2025 Wed Aug 27 02:40:01 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	4
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c402t-aead027aa99df45fbf264edd9cfebab9494e5ceb67aa2a77deaff5f9cce5ed7d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-6768-1478 0000-0003-4710-2103 0000-0002-9188-1856
OpenAccessLink	https://ieeexplore.ieee.org/document/9359652
PQID	2556486149
PQPubID	85418
PageCount	15
ParticipantIDs	ieee_primary_9359652 proquest_journals_2556486149 crossref_primary_10_1109_TEVC_2021_3060811 crossref_citationtrail_10_1109_TEVC_2021_3060811
PublicationCentury	2000
PublicationDate	2021-08-01
PublicationDateYYYYMMDD	2021-08-01
PublicationDate_xml	– month: 08 year: 2021 text: 2021-08-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on evolutionary computation
PublicationTitleAbbrev	TEVC
PublicationYear	2021
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref57 ref13 ref56 ref15 ref58 ref52 ref55 liang (ref53) 2013 ref11 ref10 ref16 feoktistov (ref17) 2006 storn (ref1) 1995 ref51 ref50 škvorc (ref8) 2019 ref46 tirronen (ref30) 2009 ref45 gämperle (ref12) 2002; 10 ref47 ref41 ref44 ref43 jia (ref31) 2012; 6 sutton (ref48) 2018 ref7 ref4 ref3 ref6 ref5 yang (ref38) 2008 ref40 ref35 ref34 ref37 goodfellow (ref49) 2016 ref36 brest (ref18) 2009 ref33 zamuda (ref42) 2019 ref2 ref39 eiben (ref61) 2006 ref24 ref23 ref26 ref25 ref64 ref20 ref63 ref22 ref65 ref21 takahama (ref32) 2012 price (ref19) 2008 ref28 ref27 ref29 awad (ref54) 2016 ref60 ref62 tvrdík (ref14) 2006 suganthan (ref59) 2005 price (ref9) 2019
References_xml	– ident: ref20 doi: 10.1109/CEC.2005.1554904 – start-page: 3126 year: 2019 ident: ref8 article-title: CEC real-parameter optimization competitions: Progress from 2013 to 2018 publication-title: Proc IEEE Congr Evol Comput (CEC) – volume: 6 start-page: 343 year: 2012 ident: ref31 article-title: An improved self-adaptive control parameter of differential evolution for global optimization publication-title: Int J Digit Content Technol Appl – ident: ref10 doi: 10.1109/4235.771166 – ident: ref60 doi: 10.1162/EVCO_a_00009 – ident: ref36 doi: 10.1109/TEVC.2008.927706 – start-page: 1 year: 2012 ident: ref32 article-title: Efficient constrained optimization by the $\epsilon$ constrained rank-based differential evolution publication-title: Proc IEEE Congr Evol Comput (CEC) – ident: ref13 doi: 10.1109/CEC.2005.1554725 – volume: 10 start-page: 293 year: 2002 ident: ref12 article-title: A parameter study for differential evolution publication-title: Adv Intell Syst Fuzzy Syst Evol Comput – ident: ref37 doi: 10.1109/TEVC.2009.2014613 – ident: ref50 doi: 10.1038/nature16961 – ident: ref35 doi: 10.1145/3319619.3326747 – year: 2016 ident: ref54 article-title: Problem definitions and evaluation criteria for the CEC2017 special session and competition on single objective real-parameter numerical optimization – ident: ref47 doi: 10.1145/1830483.1830490 – ident: ref26 doi: 10.1016/j.neucom.2013.04.036 – ident: ref43 doi: 10.1016/j.knosys.2019.01.006 – start-page: 33 year: 2008 ident: ref19 publication-title: Eliminating Drift Bias From the Differential Evolution Algorithm – ident: ref57 doi: 10.1109/CEC.2018.8477908 – year: 2018 ident: ref48 publication-title: Reinforcement Learning An Introduction – start-page: 11 year: 2019 ident: ref42 article-title: Function evaluations upto 1e+12 and large population sizes assessed in distance-based success history differential evolution for 100-digit challenge and numerical optimization scenarios (DIS Hchain 1e+12): A competition entry for '100-digit challenge, and four other numerical optimization competitions' at the genetic and evolutionary computation conference (GECCO) 2019 publication-title: Proc Genet Evolut Comput Conf Companion (GECCO) doi: 10.1145/3319619.3326751 – ident: ref25 doi: 10.1145/1068009.1068177 – year: 2006 ident: ref17 publication-title: Differential Evolution In Search of Solutions – ident: ref7 doi: 10.1109/CEC.2019.8789904 – ident: ref11 doi: 10.1109/TEVC.2014.2308294 – ident: ref6 doi: 10.1109/CEC.2014.6900380 – year: 2019 ident: ref9 article-title: The 2019 100-digit challenge on real-parameter, single objective optimization: Analysis of results – ident: ref44 doi: 10.1016/j.knosys.2017.11.015 – ident: ref27 doi: 10.1109/TEVC.2010.2087271 – ident: ref16 doi: 10.1016/j.asoc.2009.02.010 – ident: ref39 doi: 10.1109/CEC.2013.6557555 – ident: ref58 doi: 10.1162/106365603321828970 – start-page: 73 year: 2009 ident: ref18 publication-title: Constrained real-parameter optimization with ?-self-adaptive differential evolution – ident: ref51 doi: 10.1007/BF02551274 – ident: ref23 doi: 10.1007/s10462-015-9452-8 – ident: ref56 doi: 10.1016/j.asoc.2014.01.038 – ident: ref65 doi: 10.1145/3321707.3321813 – year: 2013 ident: ref53 article-title: Problem definitions and evaluation criteria for the CEC 2013 special session on real-parameter optimization – ident: ref46 doi: 10.1016/j.ejor.2015.10.043 – ident: ref41 doi: 10.1109/CEC.2017.7969307 – ident: ref62 doi: 10.1109/SITIS.2010.22 – ident: ref5 doi: 10.1109/TEVC.2010.2059031 – ident: ref22 doi: 10.1109/ICACTE.2010.5579677 – ident: ref45 doi: 10.1109/CEC.2016.7743922 – ident: ref63 doi: 10.1145/2598394.2605681 – start-page: 151 year: 2006 ident: ref61 article-title: Reinforcement learning for online control of evolutionary algorithms publication-title: Proc Int Workshop Eng Self-Org Appl (ESOA) – ident: ref4 doi: 10.1007/s10462-009-9137-2 – ident: ref2 doi: 10.1023/A:1008202821328 – ident: ref29 doi: 10.1016/S0305-0548(03)00116-3 – ident: ref33 doi: 10.1109/TEVC.2014.2360890 – start-page: 199 year: 2009 ident: ref30 publication-title: Differential Evolution with Fitness Diversity Self-adaptation – ident: ref24 doi: 10.1109/TCYB.2019.2892735 – year: 2005 ident: ref59 article-title: Problem definitions and evaluation criteria for the CEC2005 special session on real-parameter optimization – start-page: 1110 year: 2008 ident: ref38 article-title: Self-adaptive differential evolution with neighborhood search publication-title: Proc IEEE Congr Evol Comput (CEC) – year: 1995 ident: ref1 publication-title: Differential evolution-A simple and efficient adaptive scheme for global optimization over continuous spaces – ident: ref21 doi: 10.1023/A:1022995128597 – ident: ref3 doi: 10.1016/j.swevo.2016.01.004 – ident: ref64 doi: 10.1145/2576768.2598360 – ident: ref15 doi: 10.1007/s10589-007-9014-3 – ident: ref40 doi: 10.1109/CEC.2017.7969336 – year: 2016 ident: ref49 publication-title: Deep Learning – start-page: 7 year: 2006 ident: ref14 article-title: Competitive differential evolution publication-title: Proc 12th Int Conf Soft Comput (MENDEL) – ident: ref28 doi: 10.1016/j.asoc.2014.11.003 – ident: ref34 doi: 10.1109/TEVC.2006.872133 – ident: ref52 doi: 10.1162/neco.1997.9.8.1735 – ident: ref55 doi: 10.1109/CEC.2017.7969456
SSID	ssj0014519
Score	2.6178055
Snippet	Differential evolution is one of the most prestigious population-based stochastic optimization algorithm for black-box problems. The performance of a...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	666
SubjectTerms	Adaptive algorithms Adaptive control Adaptive differential evolution Algorithms Convergence Deep learning Evolutionary algorithms Evolutionary computation global optimization Machine learning Markov processes Mutation Optimization policy gradient (PG) Process control Process parameters Reinforcement learning reinforcement learning (RL) Sociology Statistics
Title	Learning Adaptive Differential Evolution Algorithm From Optimization Experiences by Policy Gradient
URI	https://ieeexplore.ieee.org/document/9359652 https://www.proquest.com/docview/2556486149
Volume	25
WOSCitedRecordID	wos000679530900008&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/IET Electronic Library (IEL) (UW System Shared) customDbUrl: eissn: 1941-0026 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014519 issn: 1089-778X databaseCode: RIE dateStart: 19970101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED4VxAADjwKiUJAHJkSgSZM4HitoYUDAAKhb5McZkPpSKEj8e86JW0AgJLYM5yjSd2d_F999B3AoW5b8hEeBzDIVxMTpA5UaERiLYeiSMVsWyD5c8evrrN8XtzU4nvfCIGJZfIYn7rG8yzdj_ep-lZ26LtI0oQ13gfO06tWa3xg4mZSqmF4QY8z6_gYzbInTu-7DGWWCUXhC_JiOwPDbGVQOVfmxE5fHS2_tfx-2DqueRrJOhfsG1HBUh7XZiAbmI7YOK1_0Buuw7Khlpcy8CdpLqz6yjpETt-uxcz8thaJ-wLpv3itZZ_A4Lp6nT0PWK8ZDdkPGQ9--yT6lkl-YemeVzDC7KMpKsukW3Pe6d2eXgR-5EGhKJKeBJMeiRFVKIYyNE6ssESY0RmiLSioRixgTjSolk0hyblBam1ihNSZouGlvw-JoPMIdYBgpFfNUOcIXty3PTGrabbRaqCgh0wa0ZiDk2uuRu7EYg7zMS1oid7jlDrfc49aAo_mSSSXG8ZfxpgNqbugxakBzhnTuw_UldzpscUZMRez-vmoPlt27q8q_JixOi1fchyX9RqAVB6UnfgAOkN7k
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9tAEB4hqAQcoA0gwqPsoSeEwXbWjz1GNCkVacohoNysfcymlfJAJiDx75m1N2krEFJvPszKlr6Z3W-8M98AfJGhJT_J4kDmuQo4cfpApUYExmIUuWTMVgWyd72s38-HQ3GzAmfLXhhErIrP8Nw9Vnf5ZqYf3a-yC9dFmia04a4lnMdh3a21vDNwQil1Ob0gzpgP_R1mFIqLQefuknLBODonhkyHYPTPKVSNVXm1F1cHTHf7_z7tI2x5IsnaNfKfYAWnDdheDGlgPmYbsPmX4mADNhy5rLWZd0B7cdURaxt57_Y99tXPS6G4H7POk_dL1h6PZuXv-a8J65azCftJxhPfwMn-iCU_MPXMaqFh9q2sasnmu3Db7QwurwI_dCHQlErOA0muRamqlEIYyxOrLFEmNEZoi0oqwQXHRKNKySSWWWZQWptYoTUmaDLT2oPV6WyK-8AwVopnqXKUj7dslpvUtFpotVBxQqZNCBcgFNorkrvBGOOiykxCUTjcCodb4XFrwulyyX0tx_Ge8Y4DamnoMWrC0QLpwgfsQ-GU2HhOXEUcvL3qBNavBj96Re97__oQNtx76jrAI1idl494DB_0EwFYfq688gXHteIr
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=Learning+Adaptive+Differential+Evolution+Algorithm+From+Optimization+Experiences+by+Policy+Gradient&rft.jtitle=IEEE+transactions+on+evolutionary+computation&rft.au=Sun%2C+Jianyong&rft.au=Liu%2C+Xin&rft.au=Back%2C+Thomas&rft.au=Xu%2C+Zongben&rft.date=2021-08-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1089-778X&rft.eissn=1941-0026&rft.volume=25&rft.issue=4&rft.spage=666&rft_id=info:doi/10.1109%2FTEVC.2021.3060811&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1089-778X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1089-778X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1089-778X&client=summon