An offline-online learning framework combining meta-learning and reinforcement learning for evolutionary multi-objective optimization

•An offline-online learning framework combining meta-learning and reinforcement learning (O2-MRL) is first proposed for evolutionary multi-objective optimization. O2-MRL can adaptively select and schedule the most appropriate MOEAs for diverse MOPs, thereby fully leveraging the complementary strengt...

Full description

Saved in:
Bibliographic Details
Published in:Swarm and evolutionary computation Vol. 97; p. 102037
Main Authors: Li, Shuxiang, Pang, Yongsheng, Huang, Zhaorong, Chu, Xianghua
Format: Journal Article
Language:English
Published: Elsevier B.V 01.08.2025
Subjects:
ISSN:2210-6502
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract •An offline-online learning framework combining meta-learning and reinforcement learning (O2-MRL) is first proposed for evolutionary multi-objective optimization. O2-MRL can adaptively select and schedule the most appropriate MOEAs for diverse MOPs, thereby fully leveraging the complementary strengths of different MOEAs and providing a novel perspective for solving MOPs.•O2-MRL overcomes the respective limitations of existing offline and online algorithm selection methods by integrating their advantages into a unified learning framework.•Experiments are conducted on forty-seven benchmark MOPs and two real-world MOPs. The experimental results demonstrate that O2-MRL consistently achieves superior and robust performance across diverse MOPs with varying dimensions, without increasing computational complexity.•The framework of proposed O2-MRL is flexible and applicable to various MOPs, and it can be extended to solve MOPs across different application domains. Many multi-objective evolutionary algorithms (MOEAs) have been proposed in addressing the multi-objective optimization problems (MOPs). However, the performance of MOEAs varies significantly across various MOPs and there is no single MOEA that performs well on all MOP instances. In addition, existing methods for adaptive MOEA selection still face limitations, which restrict the further optimization for MOPs. To fill these gaps and improve the efficiency of solving MOPs, this study proposes an offline-online learning framework combining meta-learning and reinforcement learning (O2-MRL). Instead of proposing a new MOEA or optimizing a strategy, O2-MRL solves MOPs by taking full advantage of the existing MOEAs and addresses the limitations of existing MOEA selection methods. O2-MRL can adaptively select the appropriate MOEAs for various types of MOPs with different dimensions (Offline) and automatically schedule the selected MOEAs during the optimization process (Online), offering a new idea for optimizing MOPs. To evaluate the performance of the proposed O2-MRL, forty-seven benchmark MOPs are used as instances, and nine representative MOEAs are selected for comparison. Comprehensive experiments demonstrate the significant efficiency of O2-MRL, as it achieves optimal solutions in 60.28 % of the MOPs across different dimensions and improves the optimization results in 48.23 % of them, with an average improvement of 8.72 %. In addition to maintaining high optimization performance, O2-MRL also demonstrates superior convergence speed and stability across various types of MOPs. Two real-world MOPs are employed to evaluate the practicality of O2-MRL, and the experimental results indicate that it achieves optimal solutions in both cases.
AbstractList •An offline-online learning framework combining meta-learning and reinforcement learning (O2-MRL) is first proposed for evolutionary multi-objective optimization. O2-MRL can adaptively select and schedule the most appropriate MOEAs for diverse MOPs, thereby fully leveraging the complementary strengths of different MOEAs and providing a novel perspective for solving MOPs.•O2-MRL overcomes the respective limitations of existing offline and online algorithm selection methods by integrating their advantages into a unified learning framework.•Experiments are conducted on forty-seven benchmark MOPs and two real-world MOPs. The experimental results demonstrate that O2-MRL consistently achieves superior and robust performance across diverse MOPs with varying dimensions, without increasing computational complexity.•The framework of proposed O2-MRL is flexible and applicable to various MOPs, and it can be extended to solve MOPs across different application domains. Many multi-objective evolutionary algorithms (MOEAs) have been proposed in addressing the multi-objective optimization problems (MOPs). However, the performance of MOEAs varies significantly across various MOPs and there is no single MOEA that performs well on all MOP instances. In addition, existing methods for adaptive MOEA selection still face limitations, which restrict the further optimization for MOPs. To fill these gaps and improve the efficiency of solving MOPs, this study proposes an offline-online learning framework combining meta-learning and reinforcement learning (O2-MRL). Instead of proposing a new MOEA or optimizing a strategy, O2-MRL solves MOPs by taking full advantage of the existing MOEAs and addresses the limitations of existing MOEA selection methods. O2-MRL can adaptively select the appropriate MOEAs for various types of MOPs with different dimensions (Offline) and automatically schedule the selected MOEAs during the optimization process (Online), offering a new idea for optimizing MOPs. To evaluate the performance of the proposed O2-MRL, forty-seven benchmark MOPs are used as instances, and nine representative MOEAs are selected for comparison. Comprehensive experiments demonstrate the significant efficiency of O2-MRL, as it achieves optimal solutions in 60.28 % of the MOPs across different dimensions and improves the optimization results in 48.23 % of them, with an average improvement of 8.72 %. In addition to maintaining high optimization performance, O2-MRL also demonstrates superior convergence speed and stability across various types of MOPs. Two real-world MOPs are employed to evaluate the practicality of O2-MRL, and the experimental results indicate that it achieves optimal solutions in both cases.
ArticleNumber 102037
Author Huang, Zhaorong
Pang, Yongsheng
Chu, Xianghua
Li, Shuxiang
Author_xml – sequence: 1
  givenname: Shuxiang
  surname: Li
  fullname: Li, Shuxiang
  organization: School of business administration, South China University of Technology, Guangzhou 510641, China
– sequence: 2
  givenname: Yongsheng
  surname: Pang
  fullname: Pang, Yongsheng
  organization: College of Management, Shenzhen University, Shenzhen 518060, China
– sequence: 3
  givenname: Zhaorong
  surname: Huang
  fullname: Huang, Zhaorong
  organization: Business School, Sichuan University, Chengdu 610064, China
– sequence: 4
  givenname: Xianghua
  surname: Chu
  fullname: Chu, Xianghua
  email: x.chu@szu.edu.cn
  organization: College of Management, Shenzhen University, Shenzhen 518060, China
BookMark eNp9UMtOwzAQ9KFIlNIv4OIfSHHsOiEHDlXFS6rEBc6Wvd4gh8SunLQV3PlvnBYhTuxlpNmZ1exckIkPHgm5ytkiZ3lx3Sz6A-7DgjMuE8OZKCdkynnOskIyfk7mfd-wNEUSyGpKvlaehrpunccs-BFoizp6599oHXWHhxDfKYTOuCPX4aCzX4X2lkZ0vg4RsEM__DGHSFOSdje44HX8oN2uHVwWTIMwuD3SsB1c5z71uL8kZ7Vue5z_4Iy83t-9rB-zzfPD03q1ySClHTIQWNW5NSgMmlJqCZzdaMsKbgptQEACIYBJzSotSg2VLJccuGBLC9IaMSPidBdi6PuItdpG16V0KmdqLFA16ligGgtUpwKT6_bkwhRt7zCqHhx6QOtiekbZ4P71fwM294PA
Cites_doi 10.1109/ACCESS.2018.2832181
10.1109/TEVC.2022.3208595
10.1016/j.ins.2022.06.056
10.1109/TEVC.2019.2940828
10.1109/TEVC.2013.2281535
10.1109/TFUZZ.2019.2945241
10.1109/TEVC.2020.2999100
10.1109/TEVC.2007.892759
10.1109/TETCI.2022.3146882
10.1109/4235.585893
10.1109/TASE.2019.2918691
10.1109/TAI.2024.3419757
10.1007/s11704-022-2037-1
10.1109/TEVC.2022.3186667
10.1016/j.tcs.2019.10.033
10.1016/j.eswa.2015.10.021
10.1504/IJBIC.2016.076329
10.1016/S0065-2458(08)60520-3
10.1016/j.engappai.2023.107630
10.1016/j.ins.2018.10.013
10.1162/evco_a_00236
10.1109/TEVC.2010.2064321
10.1016/j.ins.2020.08.101
10.1016/j.swevo.2023.101449
10.1109/MCI.2017.2742868
10.1016/j.engappai.2024.108646
10.3233/IDA-1997-1302
10.1109/TEVC.2019.2898886
10.1016/j.procs.2021.09.235
10.1109/TNNLS.2022.3148435
10.1162/evco_a_00242
10.1016/j.ins.2022.05.106
10.1016/j.autcon.2024.105598
10.1109/TEVC.2013.2260862
10.1109/TSMCB.2012.2227469
10.1109/TEVC.2021.3135691
ContentType Journal Article
Copyright 2025 Elsevier B.V.
Copyright_xml – notice: 2025 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.swevo.2025.102037
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
ExternalDocumentID 10_1016_j_swevo_2025_102037
S2210650225001956
GroupedDBID --K
--M
.~1
0R~
1~.
1~5
4.4
457
4G.
5VS
7-5
8P~
AAAKF
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AARIN
AATLK
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
ABAOU
ABBOA
ABGRD
ABJNI
ABMAC
ABUCO
ABWVN
ABXDB
ACDAQ
ACGFS
ACLOT
ACNNM
ACRLP
ACRPL
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADMUD
ADNMO
ADQTV
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AEQOU
AEUPX
AFJKZ
AFPUW
AFTJW
AFXIZ
AGHFR
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
APLSM
APXCP
ARUGR
AXJTR
BJAXD
BKOJK
BLXMC
EBS
EFJIC
EFKBS
EFLBG
EJD
FDB
FEDTE
FIRID
FNPLU
FYGXN
GBLVA
GBOLZ
HAMUX
HVGLF
HZ~
J1W
JJJVA
KOM
M41
MHUIS
MO0
N9A
O-L
O9-
OAUVE
P-8
P-9
PC.
Q38
ROL
SDF
SES
SPC
SPCBC
SSA
SSB
SSD
SST
SSV
SSW
SSZ
T5K
~G-
~HD
AAYXX
CITATION
ID FETCH-LOGICAL-c255t-c3e9f1dbe3beb75a5c208ad062b6abc3cb6a33c05a09a37ac95742c2304dc5db3
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001512529700002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2210-6502
IngestDate Sat Nov 29 07:36:35 EST 2025
Sat Sep 27 17:14:40 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Multi-objective optimization
Online algorithm selection
Offline algorithm selection
Meta-learning
Reinforcement learning
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c255t-c3e9f1dbe3beb75a5c208ad062b6abc3cb6a33c05a09a37ac95742c2304dc5db3
ParticipantIDs crossref_primary_10_1016_j_swevo_2025_102037
elsevier_sciencedirect_doi_10_1016_j_swevo_2025_102037
PublicationCentury 2000
PublicationDate August 2025
2025-08-00
PublicationDateYYYYMMDD 2025-08-01
PublicationDate_xml – month: 08
  year: 2025
  text: August 2025
PublicationDecade 2020
PublicationTitle Swarm and evolutionary computation
PublicationYear 2025
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Schutze, Lara, Coello (bib0022) 2011; 15
Xue, Zhang, Browne (bib0070) 2012; 43
Ishibuchi, Pang, Shang (bib0006) 2022
Li, Wang, Zhang, Ishibuchi (bib0019) 2018; 6
Qi, Li, Wang, Jin, Han (bib0026) 2022; 608
Yuan, Liu, Gu, Zhang, He (bib0061) 2021; 25
Pan, Shen, Qin, Zhang (bib0045) 2024; 166
Brazdil P, Soares, Vilalta (bib0036) 2008
Zhang, Wu, Zhang, Wang (bib0048) 2023; 34
Tian, Yang, Zhang (bib0064) 2020; 28
Cenikj, Petelin, Seiler, Cenikj, Eftimov (bib0011) 2025
Deb, Agrawal, Pratap, Meyarivan (bib0021) 2000
Qin, Zhuang, Huang, Huang (bib0043) 2021
Zhao, Liu, Zhu, Xu (bib0044) 2023
E. Zitzler, M. Laumanns, L. Thiele, SPEA2: Improving the strength Pareto evolutionary algorithm, TIK-report, 103 (2001).
Gong, Yu, Kang, Qiao, Guo, Zeng (bib0012) 2024
Yan, Tian, Liu (bib0015) 2025
Dantas, Pozo (bib0053) 2020; 805
Cui J (bib0037) 2019; 41
Zhang, Li (bib0055) 2007; 11
Zhong, Yao, Gong, Qiao, Gan, Li (bib0001) 2024
Li, Deb, Zhang (bib0002) 2019; 23
Li, Yang, Liu, Shen (bib0018) 2013
Cui, Hu, Weir, Wu (bib0035) 2016; 46
de Farias, Araújo (bib0060) 2022
Kiziloz, Deniz (bib0069) 2021
Liefooghe, Daolio, Verel, Derbel, Aguirre, Tanaka (bib0008) 2020; 24
Qiao, Yu, Qu, Liang, Yue, Ban (bib0007) 2023; 27
Ma, Yang, Wu, Ji, Zhu (bib0017) 2016
Li, Zhang, Feng, Zhou, Bai, Zhao (bib0051) 2024
Deb, Mohan, Mishra (bib0057) 2003
Chu, Li, Gao, Zhao, Cui, Huang, Yang (bib0068) 2020; 2020
Jiang, Wang, Peng (bib0024) 2020
Kerschke, Hoos, Neumann, Trautmann (bib0032) 2019; 27
Wang, Zhang, Hu (bib0046) 2024
Wolpert D H (bib0004) 1997; 1
Rice (bib0034) 1976; 15
Liu, Han, Ling, Han, Jiang (bib0059) 2023
Wen, Zhang, Xing, Ye, Li, Zhang, Wang (bib0047) 2024
Wang, Zhou, Huang (bib0049) 2024; 5
Zhao, Huang, Wang, Liu (bib0062) 2024; 135
Xue, Cai, Neri (bib0025) 2022
Wang, Gao, Lin, Huang, Suganthan (bib0042) 2023
Deb, Jain (bib0056) 2013; 18
Zhao, Zhu, Wang, Xu, Zhu, Jonrinaldi (bib0041) 2022
Gong, Cai, Chen, Ma (bib0066) 2014; 18
Kerschke (bib0005) 2019; 27
Zou, Yen, Tang, Wang (bib0010) 2021; 546
Fu, Wang, Fang, Xing, Zhang, Chen (bib0050) 2023; 17
Zitzler, Künzli (bib0023) 2004
Prusty, Patnaik, Dash, Priyadarsini Prusty (bib0040) 2024; 129
Tian, Li, Ma, Zhang, Tan, Jin (bib0009) 2023; 7
Zhang, Pan, Meng, Lu, Mou, Li (bib0030) 2022
Peng, Qiu (bib0027) 2022
Tian, Lu, Zhang, Tan, Jin (bib0063) 2020
Chu, Cai, Cui, Hu, Li, Qin (bib0033) 2019; 476
Wang, Zuo, Gong (bib0052) 2023
Cai, Ma, Gong, Tian (bib0065) 2016; 8
Zhou, Wen (bib0031) 2024
Shekhovtsov (bib0058) 2021; 192
Tian, Cheng, Zhang, Jin (bib0054) 2017; 12
Liu (bib0067) 1997; 1
Wu, Zhou, Zhu, Xia, Wen (bib0028) 2019; 17
Xu, Chen, Shi, Ruan, Wu, Zhang (bib0038) 2024
Yi, Zhang, Bai, Zhou, Yao (bib0003) 2022; 26
Vodopija, Tušar, Filipič (bib0014) 2022; 607
Alsouly, Kirley, Muñoz (bib0013) 2023; 27
Yuan, Liu, Yang (bib0016) 2024; 84
Wang, Li, Chen, Chen (bib0029) 2023
Verma, Kumar, Singh (bib0039) 2023
Tian (10.1016/j.swevo.2025.102037_bib0054) 2017; 12
Zhao (10.1016/j.swevo.2025.102037_bib0044) 2023
Yuan (10.1016/j.swevo.2025.102037_bib0016) 2024; 84
Xue (10.1016/j.swevo.2025.102037_bib0025) 2022
Deb (10.1016/j.swevo.2025.102037_bib0057) 2003
Yuan (10.1016/j.swevo.2025.102037_bib0061) 2021; 25
10.1016/j.swevo.2025.102037_bib0020
Kerschke (10.1016/j.swevo.2025.102037_bib0032) 2019; 27
Liu (10.1016/j.swevo.2025.102037_bib0067) 1997; 1
Gong (10.1016/j.swevo.2025.102037_bib0012) 2024
Schutze (10.1016/j.swevo.2025.102037_bib0022) 2011; 15
Deb (10.1016/j.swevo.2025.102037_bib0021) 2000
Chu (10.1016/j.swevo.2025.102037_bib0033) 2019; 476
Zhang (10.1016/j.swevo.2025.102037_bib0048) 2023; 34
Zhao (10.1016/j.swevo.2025.102037_bib0062) 2024; 135
Brazdil P (10.1016/j.swevo.2025.102037_bib0036) 2008
Li (10.1016/j.swevo.2025.102037_bib0051) 2024
Qi (10.1016/j.swevo.2025.102037_bib0026) 2022; 608
Zou (10.1016/j.swevo.2025.102037_bib0010) 2021; 546
Cenikj (10.1016/j.swevo.2025.102037_bib0011) 2025
Zhao (10.1016/j.swevo.2025.102037_bib0041) 2022
Shekhovtsov (10.1016/j.swevo.2025.102037_bib0058) 2021; 192
Yi (10.1016/j.swevo.2025.102037_bib0003) 2022; 26
Vodopija (10.1016/j.swevo.2025.102037_bib0014) 2022; 607
Ishibuchi (10.1016/j.swevo.2025.102037_bib0006) 2022
Wu (10.1016/j.swevo.2025.102037_bib0028) 2019; 17
Gong (10.1016/j.swevo.2025.102037_bib0066) 2014; 18
Tian (10.1016/j.swevo.2025.102037_bib0063) 2020
Zhang (10.1016/j.swevo.2025.102037_bib0030) 2022
Wang (10.1016/j.swevo.2025.102037_bib0042) 2023
Peng (10.1016/j.swevo.2025.102037_bib0027) 2022
Rice (10.1016/j.swevo.2025.102037_bib0034) 1976; 15
de Farias (10.1016/j.swevo.2025.102037_bib0060) 2022
Wang (10.1016/j.swevo.2025.102037_bib0049) 2024; 5
Tian (10.1016/j.swevo.2025.102037_bib0009) 2023; 7
Ma (10.1016/j.swevo.2025.102037_bib0017) 2016
Zhang (10.1016/j.swevo.2025.102037_bib0055) 2007; 11
Kiziloz (10.1016/j.swevo.2025.102037_bib0069) 2021
Deb (10.1016/j.swevo.2025.102037_bib0056) 2013; 18
Liu (10.1016/j.swevo.2025.102037_bib0059) 2023
Xu (10.1016/j.swevo.2025.102037_bib0038) 2024
Li (10.1016/j.swevo.2025.102037_bib0019) 2018; 6
Li (10.1016/j.swevo.2025.102037_bib0018) 2013
Cui (10.1016/j.swevo.2025.102037_bib0035) 2016; 46
Prusty (10.1016/j.swevo.2025.102037_bib0040) 2024; 129
Jiang (10.1016/j.swevo.2025.102037_bib0024) 2020
Zitzler (10.1016/j.swevo.2025.102037_bib0023) 2004
Alsouly (10.1016/j.swevo.2025.102037_bib0013) 2023; 27
Yan (10.1016/j.swevo.2025.102037_bib0015) 2025
Wang (10.1016/j.swevo.2025.102037_bib0029) 2023
Fu (10.1016/j.swevo.2025.102037_bib0050) 2023; 17
Qin (10.1016/j.swevo.2025.102037_bib0043) 2021
Wolpert D H (10.1016/j.swevo.2025.102037_bib0004) 1997; 1
Zhou (10.1016/j.swevo.2025.102037_bib0031) 2024
Zhong (10.1016/j.swevo.2025.102037_bib0001) 2024
Qiao (10.1016/j.swevo.2025.102037_bib0007) 2023; 27
Wang (10.1016/j.swevo.2025.102037_bib0046) 2024
Wang (10.1016/j.swevo.2025.102037_bib0052) 2023
Chu (10.1016/j.swevo.2025.102037_bib0068) 2020; 2020
Kerschke (10.1016/j.swevo.2025.102037_bib0005) 2019; 27
Verma (10.1016/j.swevo.2025.102037_bib0039) 2023
Pan (10.1016/j.swevo.2025.102037_bib0045) 2024; 166
Cui J (10.1016/j.swevo.2025.102037_bib0037) 2019; 41
Dantas (10.1016/j.swevo.2025.102037_bib0053) 2020; 805
Xue (10.1016/j.swevo.2025.102037_bib0070) 2012; 43
Tian (10.1016/j.swevo.2025.102037_bib0064) 2020; 28
Liefooghe (10.1016/j.swevo.2025.102037_bib0008) 2020; 24
Li (10.1016/j.swevo.2025.102037_bib0002) 2019; 23
Wen (10.1016/j.swevo.2025.102037_bib0047) 2024
Cai (10.1016/j.swevo.2025.102037_bib0065) 2016; 8
References_xml – start-page: 89
  year: 2024
  ident: bib0012
  article-title: A surrogate-assisted evolutionary algorithm with dual restricted Boltzmann machines and reinforcement learning-based adaptive strategy selection
  publication-title: Swarm Evol. Comput.
– start-page: 207
  year: 2023
  ident: bib0039
  article-title: A meta-learning framework for recommending CNN models for plant disease identification tasks
  publication-title: Comput. Electron. Agric.
– volume: 27
  start-page: 949
  year: 2023
  end-page: 963
  ident: bib0007
  article-title: Feature extraction for recommendation of constrained multiobjective evolutionary algorithms
  publication-title: IEEE Trans. Evol. Comput.
– start-page: 147
  year: 2023
  ident: bib0044
  article-title: Jonrinaldi, A selection hyper-heuristic algorithm with Q-learning mechanism
  publication-title: Appl. Soft Comput.
– start-page: 118
  year: 2022
  ident: bib0027
  article-title: A decomposition-based constrained multi-objective evolutionary algorithm with a local infeasibility utilization mechanism for UAV path planning
  publication-title: Appl. Soft Comput.
– volume: 17
  start-page: 166
  year: 2019
  end-page: 176
  ident: bib0028
  article-title: MOELS: multiobjective evolutionary list scheduling for cloud workflows
  publication-title: IEEE Trans. Autom. Sci. Eng.
– volume: 5
  start-page: 5561
  year: 2024
  end-page: 5574
  ident: bib0049
  article-title: A novel incentive mechanism for federated learning over wireless communications
  publication-title: IEEE Trans. Artif. Intell.
– volume: 2020
  start-page: 1
  year: 2020
  end-page: 13
  ident: bib0068
  article-title: A binary superior tracking artificial bee colony with dynamic cauchy mutation for feature selection
  publication-title: Complexity
– start-page: 261
  year: 2013
  end-page: 275
  ident: bib0018
  article-title: A comparative study on evolutionary algorithms for many-objective optimization
  publication-title: International Conference on Evolutionary Multi-Criterion Optimization
– volume: 46
  start-page: 33
  year: 2016
  end-page: 44
  ident: bib0035
  article-title: A recommendation system for meta-modeling: a meta-learning based approach
  publication-title: Expert Syst. Appl.
– volume: 805
  start-page: 62
  year: 2020
  end-page: 75
  ident: bib0053
  article-title: On the use of fitness landscape features in meta-learning based algorithm selection for the quadratic assignment problem
  publication-title: Theor. Comput. Sci.
– volume: 546
  start-page: 815
  year: 2021
  end-page: 834
  ident: bib0010
  article-title: A reinforcement learning approach for dynamic multi-objective optimization
  publication-title: Inf. Sci.
– start-page: 75
  year: 2022
  ident: bib0041
  article-title: An offline learning co-evolutionary algorithm with problem-specific knowledge
  publication-title: Swarm Evol. Comput.
– volume: 23
  start-page: 987
  year: 2019
  end-page: 999
  ident: bib0002
  article-title: Variable-length pareto optimization via decomposition-based evolutionary multiobjective algorithm
  publication-title: IEEE Trans. Evol. Comput.
– volume: 1
  start-page: 67
  year: 1997
  end-page: 82
  ident: bib0004
  article-title: No free lunch theorems for search
  publication-title: IEEE Trans Evol. Comput.
– start-page: 83
  year: 2023
  ident: bib0059
  article-title: A many-objective optimization evolutionary algorithm based on hyper-dominance degree
  publication-title: Swarm Evol. Comput.
– volume: 28
  start-page: 2841
  year: 2020
  end-page: 2855
  ident: bib0064
  article-title: An evolutionary multiobjective optimization based fuzzy method for overlapping community detection
  publication-title: IEEE Trans. Fuzzy Syst.
– volume: 24
  start-page: 1063
  year: 2020
  end-page: 1077
  ident: bib0008
  article-title: Landscape-aware performance prediction for evolutionary multiobjective optimization
  publication-title: IEEE Trans. Evol. Comput.
– volume: 18
  start-page: 82
  year: 2014
  end-page: 97
  ident: bib0066
  article-title: Complex network clustering by multiobjective discrete particle swarm optimization based on decomposition
  publication-title: IEEE Trans. Evol. Comput.
– start-page: 58
  year: 2020
  ident: bib0024
  article-title: Solving energy-efficient distributed job shop scheduling via multi-objective evolutionary algorithm with decomposition
  publication-title: Swarm Evol. Comput.
– start-page: 190
  year: 2024
  ident: bib0031
  article-title: A mutli-objective artificial electric field algorithm with reinforcement learning for milk-run assembly line feeding and scheduling problem
  publication-title: Comput. Ind. Eng.
– volume: 26
  start-page: 334
  year: 2022
  end-page: 348
  ident: bib0003
  article-title: Multifactorial evolutionary algorithm based on improved dynamical decomposition for many-objective optimization problems
  publication-title: IEEE Trans. Evol. Comput.
– volume: 12
  start-page: 73
  year: 2017
  end-page: 87
  ident: bib0054
  article-title: PlatEMO: a MATLAB platform for evolutionary multi-objective optimization [educational forum
  publication-title: IEEE Comput. Intell. Mag.
– volume: 8
  start-page: 84
  year: 2016
  end-page: 98
  ident: bib0065
  article-title: A survey on network community detection based on evolutionary computation
  publication-title: Int. J. Bio-Inspir. Comput.
– volume: 6
  start-page: 26194
  year: 2018
  end-page: 26214
  ident: bib0019
  article-title: Evolutionary many-objective optimization: A comparative study of the State-of-the-art
  publication-title: IEEE Access
– volume: 41
  start-page: 153
  year: 2019
  end-page: 160
  ident: bib0037
  article-title: An intelligent recommendation system for optimization algorithms based on multi-classification support vector machine and its empirical analysis
  publication-title: Comput. Eng. Sci.
– start-page: 662
  year: 2024
  ident: bib0038
  article-title: 3D meta-classification: a meta-learning approach for selecting 3D point-cloud classification algorithm
  publication-title: Inf. Sci.
– volume: 607
  start-page: 244
  year: 2022
  end-page: 262
  ident: bib0014
  article-title: Characterization of constrained continuous multiobjective optimization problems: A feature space perspective
  publication-title: Inf. Sci.
– start-page: 147
  year: 2023
  ident: bib0042
  article-title: Problem feature based meta-heuristics with Q-learning for solving urban traffic light scheduling problems
  publication-title: Appl. Soft Comput.
– start-page: 849
  year: 2000
  end-page: 858
  ident: bib0021
  article-title: A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: NSGA-II
  publication-title: International Conference on Parallel Problem Solving from Nature
– volume: 84
  year: 2024
  ident: bib0016
  article-title: An adaptive parental guidance strategy and its derived indicator-based evolutionary algorithm for multi- and many-objective optimization
  publication-title: Swarm Evol. Comput.
– volume: 25
  start-page: 75
  year: 2021
  end-page: 86
  ident: bib0061
  article-title: Investigating the properties of indicators and an evolutionary many-objective algorithm using promising regions
  publication-title: IEEE Trans. Evol. Comput.
– volume: 7
  start-page: 1051
  year: 2023
  end-page: 1064
  ident: bib0009
  article-title: Deep reinforcement Learning based adaptive operator selection for evolutionary multi-objective optimization
  publication-title: IEEE Trans. Emerg. Top. Comput. Intell.
– start-page: 222
  year: 2003
  end-page: 236
  ident: bib0057
  article-title: Towards a quick computation of well-spread pareto-optimal solutions
  publication-title: Evolutionary Multi-Criterion Optimization: Second International Conference
– start-page: 94
  year: 2025
  ident: bib0015
  article-title: An indicator-based multi-objective evolutionary algorithm assisted by improved graph convolutional networks
  publication-title: Swarm Evol. Comput.
– volume: 129
  year: 2024
  ident: bib0040
  article-title: SEMeL-LR: an improvised modeling approach using a meta-learning algorithm to classify breast cancer
  publication-title: Eng. Appl. Artif. Intell.
– start-page: 87
  year: 2024
  ident: bib0001
  article-title: A dual-population-based evolutionary algorithm for multi-objective optimization problems with irregular Pareto fronts
  publication-title: Swarm Evol. Comput.
– start-page: 197
  year: 2024
  ident: bib0046
  article-title: A Q-learning based hyper-heuristic scheduling algorithm with multi-rule selection for sub-assembly in shipbuilding
  publication-title: Comput. Ind. Eng.
– start-page: 156
  year: 2021
  ident: bib0043
  article-title: A novel reinforcement learning-based hyper-heuristic for heterogeneous vehicle routing problem
  publication-title: Comput. Ind. Eng.
– volume: 15
  start-page: 65
  year: 1976
  end-page: 118
  ident: bib0034
  article-title: The algorithm selection problem
  publication-title: Adv. Comput.
– volume: 27
  start-page: 99
  year: 2019
  end-page: 127
  ident: bib0005
  article-title: H., automated algorithm selection on continuous black-box problems by combining exploratory landscape analysis and machine learning
  publication-title: Evol Comput
– start-page: 238
  year: 2022
  ident: bib0030
  article-title: An automatic multi-objective evolutionary algorithm for the hybrid flowshop scheduling problem with consistent sublots
  publication-title: Knowl.-Based Syst.
– volume: 43
  start-page: 1656
  year: 2012
  end-page: 1671
  ident: bib0070
  article-title: Particle swarm optimization for feature selection in classification: a multi-objective approach
  publication-title: IEEE trans. Cybern.
– start-page: 2477
  year: 2016
  end-page: 2483
  ident: bib0017
  article-title: A comparative study on decomposition-based multi-objective evolutionary algorithms for many-objective optimization
  publication-title: IEEE Congr. Evol. Comput. (CEC)
– volume: 11
  start-page: 712
  year: 2007
  end-page: 731
  ident: bib0055
  article-title: MOEA/D: a multiobjective evolutionary algorithm based on decomposition
  publication-title: IEEE Trans. Evol. Comput.
– volume: 192
  start-page: 4570
  year: 2021
  end-page: 4577
  ident: bib0058
  article-title: How strongly do rank similarity coefficients differ used in decision making problems?
  publication-title: Procedia Comput. Sci.
– volume: 166
  year: 2024
  ident: bib0045
  article-title: Deep reinforcement learning for multi-objective optimization in BIM-based green building design
  publication-title: Automat. Construct.
– volume: 135
  year: 2024
  ident: bib0062
  article-title: Carbon futures price forecasting based on feature selection
  publication-title: Eng. Appl. Artif. Intell.
– volume: 1
  start-page: 131
  year: 1997
  end-page: 156
  ident: bib0067
  article-title: Feature selection for classification
  publication-title: Intell. Data Anal.
– start-page: 68
  year: 2022
  ident: bib0060
  article-title: A decomposition-based many-objective evolutionary algorithm updating weights when required
  publication-title: Swarm Evol. Comput.
– start-page: 937
  year: 2022
  end-page: 957
  ident: bib0006
  article-title: Difficulties in fair performance comparison of multiobjective evolutionary algorithms
  publication-title: Proceedings of the Genetic and Evolutionary Computation Conference Companion
– volume: 27
  start-page: 3
  year: 2019
  end-page: 45
  ident: bib0032
  article-title: Automated algorithm selection: survey and perspectives
  publication-title: Evol. Comput.
– year: 2020
  ident: bib0063
  article-title: Solving large-scale multiobjective optimization problems with sparse optimal solutions via unsupervised neural networks
  publication-title: IEEE Trans. Cybern.
– start-page: 832
  year: 2004
  end-page: 842
  ident: bib0023
  article-title: Indicator-based selection in multiobjective search
  publication-title: International Conference on Parallel Problem Solving from Nature
– start-page: 94
  year: 2025
  ident: bib0011
  article-title: Landscape features in single-objective continuous optimization: have we hit a wall in algorithm selection generalization?
  publication-title: Swarm Evol. Comput.
– start-page: 216
  year: 2023
  ident: bib0029
  article-title: Medical machine learning based on multiobjective evolutionary algorithm using learning decomposition
  publication-title: Expert Syst. Appl.
– volume: 17
  year: 2023
  ident: bib0050
  article-title: MAML2: meta reinforcement learning via meta-learning for task categories
  publication-title: Front. Comput. Sci.
– year: 2008
  ident: bib0036
  article-title: Metalearning: Applications to Data Mining
– volume: 34
  start-page: 7978
  year: 2023
  end-page: 7991
  ident: bib0048
  article-title: Meta-learning-based deep reinforcement learning for multiobjective optimization problems
  publication-title: IEEE Trans. Neural. Netw. Learn. Syst.
– volume: 15
  start-page: 444
  year: 2011
  end-page: 455
  ident: bib0022
  article-title: On the influence of the number of objectives on the hardness of a multiobjective optimization problem
  publication-title: IEEE Trans. Evol. Comput.
– start-page: 162
  year: 2024
  ident: bib0051
  article-title: Multi-objective two-stage robust optimization of wind/PV/thermal power system based on meta multi-agent reinforcement learning
  publication-title: Int. J. Electr. Power Energy Syst.
– start-page: 193
  year: 2024
  ident: bib0047
  article-title: An improved genetic algorithm based on reinforcement learning for aircraft assembly scheduling problem
  publication-title: Comput. Ind. Eng.
– volume: 27
  start-page: 1427
  year: 2023
  end-page: 1439
  ident: bib0013
  article-title: An instance space analysis of constrained multiobjective optimization problems
  publication-title: IEEE Trans. Evol. Comput.
– volume: 18
  start-page: 577
  year: 2013
  end-page: 601
  ident: bib0056
  article-title: An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: solving problems with box constraints
  publication-title: IEEE trans. Evol. Comput.
– volume: 476
  start-page: 192
  year: 2019
  end-page: 210
  ident: bib0033
  article-title: Adaptive recommendation model using meta-learning for population-based algorithms
  publication-title: Inf. Sci.
– start-page: 649
  year: 2023
  ident: bib0052
  article-title: Migration-based algorithm library enrichment for constrained multi-objective optimization and applications in algorithm selection
  publication-title: Inf. Sci.
– start-page: 127
  year: 2022
  ident: bib0025
  article-title: A multi-objective evolutionary algorithm with interval based initialization and self-adaptive crossover operator for large-scale feature selection in classification
  publication-title: Appl. Soft Comput.
– start-page: 159
  year: 2021
  ident: bib0069
  article-title: An evolutionary parallel multiobjective feature selection framework
  publication-title: Comput. Ind. Eng.
– reference: E. Zitzler, M. Laumanns, L. Thiele, SPEA2: Improving the strength Pareto evolutionary algorithm, TIK-report, 103 (2001).
– volume: 608
  start-page: 178
  year: 2022
  end-page: 201
  ident: bib0026
  article-title: QMOEA: A Q-learning-based multiobjective evolutionary algorithm for solving time-dependent green vehicle routing problems with time windows
  publication-title: Inf. Sci.
– start-page: 94
  year: 2025
  ident: 10.1016/j.swevo.2025.102037_bib0015
  article-title: An indicator-based multi-objective evolutionary algorithm assisted by improved graph convolutional networks
  publication-title: Swarm Evol. Comput.
– start-page: 147
  year: 2023
  ident: 10.1016/j.swevo.2025.102037_bib0042
  article-title: Problem feature based meta-heuristics with Q-learning for solving urban traffic light scheduling problems
  publication-title: Appl. Soft Comput.
– start-page: 216
  year: 2023
  ident: 10.1016/j.swevo.2025.102037_bib0029
  article-title: Medical machine learning based on multiobjective evolutionary algorithm using learning decomposition
  publication-title: Expert Syst. Appl.
– volume: 6
  start-page: 26194
  year: 2018
  ident: 10.1016/j.swevo.2025.102037_bib0019
  article-title: Evolutionary many-objective optimization: A comparative study of the State-of-the-art
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2018.2832181
– start-page: 156
  year: 2021
  ident: 10.1016/j.swevo.2025.102037_bib0043
  article-title: A novel reinforcement learning-based hyper-heuristic for heterogeneous vehicle routing problem
  publication-title: Comput. Ind. Eng.
– volume: 27
  start-page: 1427
  year: 2023
  ident: 10.1016/j.swevo.2025.102037_bib0013
  article-title: An instance space analysis of constrained multiobjective optimization problems
  publication-title: IEEE Trans. Evol. Comput.
  doi: 10.1109/TEVC.2022.3208595
– volume: 608
  start-page: 178
  year: 2022
  ident: 10.1016/j.swevo.2025.102037_bib0026
  article-title: QMOEA: A Q-learning-based multiobjective evolutionary algorithm for solving time-dependent green vehicle routing problems with time windows
  publication-title: Inf. Sci.
  doi: 10.1016/j.ins.2022.06.056
– volume: 24
  start-page: 1063
  year: 2020
  ident: 10.1016/j.swevo.2025.102037_bib0008
  article-title: Landscape-aware performance prediction for evolutionary multiobjective optimization
  publication-title: IEEE Trans. Evol. Comput.
  doi: 10.1109/TEVC.2019.2940828
– start-page: 162
  year: 2024
  ident: 10.1016/j.swevo.2025.102037_bib0051
  article-title: Multi-objective two-stage robust optimization of wind/PV/thermal power system based on meta multi-agent reinforcement learning
  publication-title: Int. J. Electr. Power Energy Syst.
– volume: 18
  start-page: 577
  year: 2013
  ident: 10.1016/j.swevo.2025.102037_bib0056
  article-title: An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: solving problems with box constraints
  publication-title: IEEE trans. Evol. Comput.
  doi: 10.1109/TEVC.2013.2281535
– volume: 28
  start-page: 2841
  year: 2020
  ident: 10.1016/j.swevo.2025.102037_bib0064
  article-title: An evolutionary multiobjective optimization based fuzzy method for overlapping community detection
  publication-title: IEEE Trans. Fuzzy Syst.
  doi: 10.1109/TFUZZ.2019.2945241
– start-page: 937
  year: 2022
  ident: 10.1016/j.swevo.2025.102037_bib0006
  article-title: Difficulties in fair performance comparison of multiobjective evolutionary algorithms
– start-page: 261
  year: 2013
  ident: 10.1016/j.swevo.2025.102037_bib0018
  article-title: A comparative study on evolutionary algorithms for many-objective optimization
– start-page: 207
  year: 2023
  ident: 10.1016/j.swevo.2025.102037_bib0039
  article-title: A meta-learning framework for recommending CNN models for plant disease identification tasks
  publication-title: Comput. Electron. Agric.
– volume: 25
  start-page: 75
  year: 2021
  ident: 10.1016/j.swevo.2025.102037_bib0061
  article-title: Investigating the properties of indicators and an evolutionary many-objective algorithm using promising regions
  publication-title: IEEE Trans. Evol. Comput.
  doi: 10.1109/TEVC.2020.2999100
– start-page: 94
  year: 2025
  ident: 10.1016/j.swevo.2025.102037_bib0011
  article-title: Landscape features in single-objective continuous optimization: have we hit a wall in algorithm selection generalization?
  publication-title: Swarm Evol. Comput.
– ident: 10.1016/j.swevo.2025.102037_bib0020
– volume: 11
  start-page: 712
  year: 2007
  ident: 10.1016/j.swevo.2025.102037_bib0055
  article-title: MOEA/D: a multiobjective evolutionary algorithm based on decomposition
  publication-title: IEEE Trans. Evol. Comput.
  doi: 10.1109/TEVC.2007.892759
– volume: 7
  start-page: 1051
  year: 2023
  ident: 10.1016/j.swevo.2025.102037_bib0009
  article-title: Deep reinforcement Learning based adaptive operator selection for evolutionary multi-objective optimization
  publication-title: IEEE Trans. Emerg. Top. Comput. Intell.
  doi: 10.1109/TETCI.2022.3146882
– volume: 1
  start-page: 67
  year: 1997
  ident: 10.1016/j.swevo.2025.102037_bib0004
  article-title: No free lunch theorems for search
  publication-title: IEEE Trans Evol. Comput.
  doi: 10.1109/4235.585893
– volume: 17
  start-page: 166
  year: 2019
  ident: 10.1016/j.swevo.2025.102037_bib0028
  article-title: MOELS: multiobjective evolutionary list scheduling for cloud workflows
  publication-title: IEEE Trans. Autom. Sci. Eng.
  doi: 10.1109/TASE.2019.2918691
– volume: 41
  start-page: 153
  year: 2019
  ident: 10.1016/j.swevo.2025.102037_bib0037
  article-title: An intelligent recommendation system for optimization algorithms based on multi-classification support vector machine and its empirical analysis
  publication-title: Comput. Eng. Sci.
– volume: 5
  start-page: 5561
  year: 2024
  ident: 10.1016/j.swevo.2025.102037_bib0049
  article-title: A novel incentive mechanism for federated learning over wireless communications
  publication-title: IEEE Trans. Artif. Intell.
  doi: 10.1109/TAI.2024.3419757
– volume: 17
  year: 2023
  ident: 10.1016/j.swevo.2025.102037_bib0050
  article-title: MAML2: meta reinforcement learning via meta-learning for task categories
  publication-title: Front. Comput. Sci.
  doi: 10.1007/s11704-022-2037-1
– start-page: 87
  year: 2024
  ident: 10.1016/j.swevo.2025.102037_bib0001
  article-title: A dual-population-based evolutionary algorithm for multi-objective optimization problems with irregular Pareto fronts
  publication-title: Swarm Evol. Comput.
– volume: 27
  start-page: 949
  year: 2023
  ident: 10.1016/j.swevo.2025.102037_bib0007
  article-title: Feature extraction for recommendation of constrained multiobjective evolutionary algorithms
  publication-title: IEEE Trans. Evol. Comput.
  doi: 10.1109/TEVC.2022.3186667
– volume: 2020
  start-page: 1
  year: 2020
  ident: 10.1016/j.swevo.2025.102037_bib0068
  article-title: A binary superior tracking artificial bee colony with dynamic cauchy mutation for feature selection
  publication-title: Complexity
– start-page: 832
  year: 2004
  ident: 10.1016/j.swevo.2025.102037_bib0023
  article-title: Indicator-based selection in multiobjective search
– volume: 805
  start-page: 62
  year: 2020
  ident: 10.1016/j.swevo.2025.102037_bib0053
  article-title: On the use of fitness landscape features in meta-learning based algorithm selection for the quadratic assignment problem
  publication-title: Theor. Comput. Sci.
  doi: 10.1016/j.tcs.2019.10.033
– volume: 46
  start-page: 33
  year: 2016
  ident: 10.1016/j.swevo.2025.102037_bib0035
  article-title: A recommendation system for meta-modeling: a meta-learning based approach
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2015.10.021
– volume: 8
  start-page: 84
  year: 2016
  ident: 10.1016/j.swevo.2025.102037_bib0065
  article-title: A survey on network community detection based on evolutionary computation
  publication-title: Int. J. Bio-Inspir. Comput.
  doi: 10.1504/IJBIC.2016.076329
– start-page: 83
  year: 2023
  ident: 10.1016/j.swevo.2025.102037_bib0059
  article-title: A many-objective optimization evolutionary algorithm based on hyper-dominance degree
  publication-title: Swarm Evol. Comput.
– volume: 15
  start-page: 65
  year: 1976
  ident: 10.1016/j.swevo.2025.102037_bib0034
  article-title: The algorithm selection problem
  publication-title: Adv. Comput.
  doi: 10.1016/S0065-2458(08)60520-3
– start-page: 197
  year: 2024
  ident: 10.1016/j.swevo.2025.102037_bib0046
  article-title: A Q-learning based hyper-heuristic scheduling algorithm with multi-rule selection for sub-assembly in shipbuilding
  publication-title: Comput. Ind. Eng.
– start-page: 147
  year: 2023
  ident: 10.1016/j.swevo.2025.102037_bib0044
  article-title: Jonrinaldi, A selection hyper-heuristic algorithm with Q-learning mechanism
  publication-title: Appl. Soft Comput.
– volume: 129
  year: 2024
  ident: 10.1016/j.swevo.2025.102037_bib0040
  article-title: SEMeL-LR: an improvised modeling approach using a meta-learning algorithm to classify breast cancer
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2023.107630
– start-page: 75
  year: 2022
  ident: 10.1016/j.swevo.2025.102037_bib0041
  article-title: An offline learning co-evolutionary algorithm with problem-specific knowledge
  publication-title: Swarm Evol. Comput.
– start-page: 127
  year: 2022
  ident: 10.1016/j.swevo.2025.102037_bib0025
  article-title: A multi-objective evolutionary algorithm with interval based initialization and self-adaptive crossover operator for large-scale feature selection in classification
  publication-title: Appl. Soft Comput.
– volume: 476
  start-page: 192
  year: 2019
  ident: 10.1016/j.swevo.2025.102037_bib0033
  article-title: Adaptive recommendation model using meta-learning for population-based algorithms
  publication-title: Inf. Sci.
  doi: 10.1016/j.ins.2018.10.013
– volume: 27
  start-page: 99
  year: 2019
  ident: 10.1016/j.swevo.2025.102037_bib0005
  article-title: H., automated algorithm selection on continuous black-box problems by combining exploratory landscape analysis and machine learning
  publication-title: Evol Comput
  doi: 10.1162/evco_a_00236
– start-page: 118
  year: 2022
  ident: 10.1016/j.swevo.2025.102037_bib0027
  article-title: A decomposition-based constrained multi-objective evolutionary algorithm with a local infeasibility utilization mechanism for UAV path planning
  publication-title: Appl. Soft Comput.
– start-page: 58
  year: 2020
  ident: 10.1016/j.swevo.2025.102037_bib0024
  article-title: Solving energy-efficient distributed job shop scheduling via multi-objective evolutionary algorithm with decomposition
  publication-title: Swarm Evol. Comput.
– volume: 15
  start-page: 444
  year: 2011
  ident: 10.1016/j.swevo.2025.102037_bib0022
  article-title: On the influence of the number of objectives on the hardness of a multiobjective optimization problem
  publication-title: IEEE Trans. Evol. Comput.
  doi: 10.1109/TEVC.2010.2064321
– volume: 546
  start-page: 815
  year: 2021
  ident: 10.1016/j.swevo.2025.102037_bib0010
  article-title: A reinforcement learning approach for dynamic multi-objective optimization
  publication-title: Inf. Sci.
  doi: 10.1016/j.ins.2020.08.101
– volume: 84
  year: 2024
  ident: 10.1016/j.swevo.2025.102037_bib0016
  article-title: An adaptive parental guidance strategy and its derived indicator-based evolutionary algorithm for multi- and many-objective optimization
  publication-title: Swarm Evol. Comput.
  doi: 10.1016/j.swevo.2023.101449
– volume: 12
  start-page: 73
  year: 2017
  ident: 10.1016/j.swevo.2025.102037_bib0054
  article-title: PlatEMO: a MATLAB platform for evolutionary multi-objective optimization [educational forum
  publication-title: IEEE Comput. Intell. Mag.
  doi: 10.1109/MCI.2017.2742868
– start-page: 222
  year: 2003
  ident: 10.1016/j.swevo.2025.102037_bib0057
  article-title: Towards a quick computation of well-spread pareto-optimal solutions
– volume: 135
  year: 2024
  ident: 10.1016/j.swevo.2025.102037_bib0062
  article-title: Carbon futures price forecasting based on feature selection
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2024.108646
– volume: 1
  start-page: 131
  year: 1997
  ident: 10.1016/j.swevo.2025.102037_bib0067
  article-title: Feature selection for classification
  publication-title: Intell. Data Anal.
  doi: 10.3233/IDA-1997-1302
– start-page: 2477
  year: 2016
  ident: 10.1016/j.swevo.2025.102037_bib0017
  article-title: A comparative study on decomposition-based multi-objective evolutionary algorithms for many-objective optimization
  publication-title: IEEE Congr. Evol. Comput. (CEC)
– start-page: 159
  year: 2021
  ident: 10.1016/j.swevo.2025.102037_bib0069
  article-title: An evolutionary parallel multiobjective feature selection framework
  publication-title: Comput. Ind. Eng.
– volume: 23
  start-page: 987
  year: 2019
  ident: 10.1016/j.swevo.2025.102037_bib0002
  article-title: Variable-length pareto optimization via decomposition-based evolutionary multiobjective algorithm
  publication-title: IEEE Trans. Evol. Comput.
  doi: 10.1109/TEVC.2019.2898886
– start-page: 849
  year: 2000
  ident: 10.1016/j.swevo.2025.102037_bib0021
  article-title: A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: NSGA-II
– volume: 192
  start-page: 4570
  year: 2021
  ident: 10.1016/j.swevo.2025.102037_bib0058
  article-title: How strongly do rank similarity coefficients differ used in decision making problems?
  publication-title: Procedia Comput. Sci.
  doi: 10.1016/j.procs.2021.09.235
– start-page: 89
  year: 2024
  ident: 10.1016/j.swevo.2025.102037_bib0012
  article-title: A surrogate-assisted evolutionary algorithm with dual restricted Boltzmann machines and reinforcement learning-based adaptive strategy selection
  publication-title: Swarm Evol. Comput.
– volume: 34
  start-page: 7978
  year: 2023
  ident: 10.1016/j.swevo.2025.102037_bib0048
  article-title: Meta-learning-based deep reinforcement learning for multiobjective optimization problems
  publication-title: IEEE Trans. Neural. Netw. Learn. Syst.
  doi: 10.1109/TNNLS.2022.3148435
– volume: 27
  start-page: 3
  year: 2019
  ident: 10.1016/j.swevo.2025.102037_bib0032
  article-title: Automated algorithm selection: survey and perspectives
  publication-title: Evol. Comput.
  doi: 10.1162/evco_a_00242
– start-page: 68
  year: 2022
  ident: 10.1016/j.swevo.2025.102037_bib0060
  article-title: A decomposition-based many-objective evolutionary algorithm updating weights when required
  publication-title: Swarm Evol. Comput.
– start-page: 662
  year: 2024
  ident: 10.1016/j.swevo.2025.102037_bib0038
  article-title: 3D meta-classification: a meta-learning approach for selecting 3D point-cloud classification algorithm
  publication-title: Inf. Sci.
– volume: 607
  start-page: 244
  year: 2022
  ident: 10.1016/j.swevo.2025.102037_bib0014
  article-title: Characterization of constrained continuous multiobjective optimization problems: A feature space perspective
  publication-title: Inf. Sci.
  doi: 10.1016/j.ins.2022.05.106
– start-page: 190
  year: 2024
  ident: 10.1016/j.swevo.2025.102037_bib0031
  article-title: A mutli-objective artificial electric field algorithm with reinforcement learning for milk-run assembly line feeding and scheduling problem
  publication-title: Comput. Ind. Eng.
– volume: 166
  year: 2024
  ident: 10.1016/j.swevo.2025.102037_bib0045
  article-title: Deep reinforcement learning for multi-objective optimization in BIM-based green building design
  publication-title: Automat. Construct.
  doi: 10.1016/j.autcon.2024.105598
– year: 2020
  ident: 10.1016/j.swevo.2025.102037_bib0063
  article-title: Solving large-scale multiobjective optimization problems with sparse optimal solutions via unsupervised neural networks
  publication-title: IEEE Trans. Cybern.
– start-page: 238
  year: 2022
  ident: 10.1016/j.swevo.2025.102037_bib0030
  article-title: An automatic multi-objective evolutionary algorithm for the hybrid flowshop scheduling problem with consistent sublots
  publication-title: Knowl.-Based Syst.
– start-page: 649
  year: 2023
  ident: 10.1016/j.swevo.2025.102037_bib0052
  article-title: Migration-based algorithm library enrichment for constrained multi-objective optimization and applications in algorithm selection
  publication-title: Inf. Sci.
– volume: 18
  start-page: 82
  year: 2014
  ident: 10.1016/j.swevo.2025.102037_bib0066
  article-title: Complex network clustering by multiobjective discrete particle swarm optimization based on decomposition
  publication-title: IEEE Trans. Evol. Comput.
  doi: 10.1109/TEVC.2013.2260862
– year: 2008
  ident: 10.1016/j.swevo.2025.102037_bib0036
– volume: 43
  start-page: 1656
  year: 2012
  ident: 10.1016/j.swevo.2025.102037_bib0070
  article-title: Particle swarm optimization for feature selection in classification: a multi-objective approach
  publication-title: IEEE trans. Cybern.
  doi: 10.1109/TSMCB.2012.2227469
– volume: 26
  start-page: 334
  year: 2022
  ident: 10.1016/j.swevo.2025.102037_bib0003
  article-title: Multifactorial evolutionary algorithm based on improved dynamical decomposition for many-objective optimization problems
  publication-title: IEEE Trans. Evol. Comput.
  doi: 10.1109/TEVC.2021.3135691
– start-page: 193
  year: 2024
  ident: 10.1016/j.swevo.2025.102037_bib0047
  article-title: An improved genetic algorithm based on reinforcement learning for aircraft assembly scheduling problem
  publication-title: Comput. Ind. Eng.
SSID ssj0000602559
Score 2.3639927
Snippet •An offline-online learning framework combining meta-learning and reinforcement learning (O2-MRL) is first proposed for evolutionary multi-objective...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 102037
SubjectTerms Meta-learning
Multi-objective optimization
Offline algorithm selection
Online algorithm selection
Reinforcement learning
Title An offline-online learning framework combining meta-learning and reinforcement learning for evolutionary multi-objective optimization
URI https://dx.doi.org/10.1016/j.swevo.2025.102037
Volume 97
WOSCitedRecordID wos001512529700002&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 2210-6502
  databaseCode: AIEXJ
  dateStart: 20110301
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0000602559
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1db9MwFLVKxwMvjE8xNpAfeBueUjtpnMdqGhpompA6pMJL5I-0oYJkaputf2B_YL9413acJitCgIQqpZFdO2nO0fW1c3wvQu8iIZjSFKwfDxQxMwYCg0JCBlzDJ1AD7pA-i8_P-WSSfO71bv1emKsfcVHw9Tq5_K9QQxmAbbbO_gXcTadQAOcAOhwBdjj-EfAj4wBOjfdIXBgMnxlidjj1SiyjJJc2NYRJIS1I8wurNs9sNFVlFw5bjW1s8PrWjdbOahFJKefOZh6WYH1-1ts62z7v-FosXCKOTnNl80l0hABnVlowzqs1kHa2ebvl7NHXspgt82xTcVrVNd9yYQIxNBXHeWWKJ6aXvBLtlQ0aNbq6erlta8uNsYoU5qgE3MqOCXcS363RwC1MzI-W1_D_jswlTKSKwEWZuRdme2w6Nv2CT2g3UT5AOzSOEt5HO6OPJ5NPzcpdMLTzMJO10N-LD2dlhYNbV_u1y9NyYy6eoMf1_AOPHG-eol5WPEO7PrcHrk39c3QzKnCXRtgzATc0wg2NcIdGGMDGHRq1GpcL3OYBvkcj3KbRC_Tlw8nF8SmpU3YQBc9kRRTLkulAy4zJTMaRiBQNuNDBkMqhkIop-GJMBZEIEsFioZIoDqkybya0irRkL1G_KIvsFcIw01daxjrMwjhMFOWKayoZD4WGATqie-i9f6rppYvMknrJ4jy1IKQGhNSBsIeG_smntXPpnMYU2PK7hq__teE-erRh9QHqrxZV9gY9VFer78vF25pVdy43qlg
linkProvider Elsevier
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=An+offline-online+learning+framework+combining+meta-learning+and+reinforcement+learning+for+evolutionary+multi-objective+optimization&rft.jtitle=Swarm+and+evolutionary+computation&rft.au=Li%2C+Shuxiang&rft.au=Pang%2C+Yongsheng&rft.au=Huang%2C+Zhaorong&rft.au=Chu%2C+Xianghua&rft.date=2025-08-01&rft.pub=Elsevier+B.V&rft.issn=2210-6502&rft.volume=97&rft_id=info:doi/10.1016%2Fj.swevo.2025.102037&rft.externalDocID=S2210650225001956
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2210-6502&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2210-6502&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2210-6502&client=summon