Neural combinatorial optimization: A tutorial

Recent advancements in deep reinforcement learning have sparked a growing interest in the application of this approach to solve combinatorial optimization (CO) problems. This paper presents neural combinatorial optimization (NCO) as a framework for constructing functions that work as heuristics for...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computers & operations research Ročník 182; s. 107102
Hlavní autoři: Angioni, Davide, Archetti, Claudia, Speranza, M. Grazia
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.10.2025
Témata:
ISSN:0305-0548
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Recent advancements in deep reinforcement learning have sparked a growing interest in the application of this approach to solve combinatorial optimization (CO) problems. This paper presents neural combinatorial optimization (NCO) as a framework for constructing functions that work as heuristics for CO problems. Given the rapid expansion of the field and the increasing interest in the topic, this tutorial introduces the main techniques utilized in NCO and explores the current open issues in the field. We define key terms and concepts related to NCO and present the latest developments, using the Knapsack Problem as a running example to complement theoretical explanations. Finally, we analyze prominent works in the field of NCO, with a focus on their application to the Traveling Salesman Problem, which serves as the most extensively studied problem in this domain. •We provide a tutorial on NCO.•We give an example on the TSP and the KP.•We provide a short code for a basic version of NCO.•We discuss some pros and cons of NCO.
AbstractList Recent advancements in deep reinforcement learning have sparked a growing interest in the application of this approach to solve combinatorial optimization (CO) problems. This paper presents neural combinatorial optimization (NCO) as a framework for constructing functions that work as heuristics for CO problems. Given the rapid expansion of the field and the increasing interest in the topic, this tutorial introduces the main techniques utilized in NCO and explores the current open issues in the field. We define key terms and concepts related to NCO and present the latest developments, using the Knapsack Problem as a running example to complement theoretical explanations. Finally, we analyze prominent works in the field of NCO, with a focus on their application to the Traveling Salesman Problem, which serves as the most extensively studied problem in this domain. •We provide a tutorial on NCO.•We give an example on the TSP and the KP.•We provide a short code for a basic version of NCO.•We discuss some pros and cons of NCO.
ArticleNumber 107102
Author Angioni, Davide
Archetti, Claudia
Speranza, M. Grazia
Author_xml – sequence: 1
  givenname: Davide
  orcidid: 0000-0002-8825-7817
  surname: Angioni
  fullname: Angioni, Davide
  email: d.angioni@unibs.it, davide.angioni@orobix.com
  organization: Department of Economics and Management, University of Brescia, Italy
– sequence: 2
  givenname: Claudia
  orcidid: 0000-0002-3524-1600
  surname: Archetti
  fullname: Archetti, Claudia
  organization: Department of Economics and Management, University of Brescia, Italy
– sequence: 3
  givenname: M. Grazia
  orcidid: 0000-0002-8893-5227
  surname: Speranza
  fullname: Speranza, M. Grazia
  email: grazia.speranza@unibs.it
  organization: Department of Economics and Management, University of Brescia, Italy
BookMark eNp9j89KxDAQh3NYwd3VB_DWF2idJE2b6mlZ1BUWveg5pPkDKdtmSbKCPr0p9ewcZvgxfMN8G7Sa_GQQusNQYcDN_VApHyoChOXcYiArtAYKrARW82u0iXGAXC3Ba1S-mUuQp0L5sXeTTD64nPw5udH9yOT89FDsinRZFjfoyspTNLd_c4s-n58-9ofy-P7yut8dS0Vxl8qaSkK7TjOtpNU1l0Rp07TMGl6ThtGeaYrl3GVnOWCLoQepKa953xpi6Rbh5a4KPsZgrDgHN8rwLTCI2VEMIjuK2VEsjpl5XBiTH_tyJoionJmU0S4YlYT27h_6F-X1XYQ
Cites_doi 10.1038/s41586-021-03544-w
10.1016/j.engappai.2022.104848
10.1109/TITS.2020.3003163
10.1007/s10601-022-09327-y
10.1038/s41586-023-06419-4
10.1109/ICMLA51294.2020.00013
10.1038/s41586-022-05172-4
10.1109/CVPR.2016.90
10.1109/IJCNN48605.2020.9207026
10.1073/pnas.79.8.2554
10.1038/nature14236
10.24963/ijcai.2021/357
10.1038/323533a0
10.1038/s41586-020-03051-4
10.1037/h0042519
10.1007/978-3-319-93031-2_12
10.1016/j.cor.2021.105400
10.1162/neco.1997.9.8.1735
10.1016/j.ejor.2020.07.063
10.1007/s11750-017-0451-6
10.1109/TNN.2008.2005605
10.1109/TII.2020.3031409
10.1109/TITS.2021.3105232
10.3115/v1/D14-1179
10.1109/ACCESS.2020.3004964
ContentType Journal Article
Copyright 2025 The Author(s)
Copyright_xml – notice: 2025 The Author(s)
DBID 6I.
AAFTH
AAYXX
CITATION
DOI 10.1016/j.cor.2025.107102
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
Business
ExternalDocumentID 10_1016_j_cor_2025_107102
S0305054825001303
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
186
1B1
1OL
1RT
1~.
1~5
29F
4.4
457
4G.
5GY
5VS
6I.
6J9
7-5
71M
8P~
9JN
9JO
AAAKF
AAAKG
AABNK
AAEDT
AAEDW
AAFJI
AAFTH
AAIKJ
AAKOC
AALRI
AAOAW
AAQXK
AARIN
AATTM
AAXKI
AAXUO
AAYFN
AAYOK
AAYWO
ABAOU
ABBOA
ABDPE
ABEFU
ABFNM
ABFRF
ABJNI
ABMAC
ABMMH
ABUCO
ABWVN
ABXDB
ACDAQ
ACGFO
ACGFS
ACNCT
ACNNM
ACRLP
ACRPL
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADGUI
ADJOM
ADMUD
ADNMO
AEBSH
AEFWE
AEHXG
AEIPS
AEKER
AENEX
AEUPX
AFFNX
AFJKZ
AFPUW
AFTJW
AFXIZ
AGCQF
AGHFR
AGQPQ
AGRNS
AGUBO
AGYEJ
AHHHB
AHZHX
AI.
AIALX
AIEXJ
AIGII
AIGVJ
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOMHK
AOUOD
APLSM
APXCP
ARUGR
ASPBG
AVARZ
AVWKF
AXJTR
AZFZN
BKOJK
BKOMP
BLXMC
BNPGV
CS3
DU5
EBS
EFJIC
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HAMUX
HVGLF
HZ~
H~9
IHE
J1W
KOM
LY1
M41
MHUIS
MO0
MS~
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
PRBVW
Q38
R2-
RIG
ROL
RPZ
RXW
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SSB
SSD
SSH
SSO
SSV
SSW
SSZ
T5K
TAE
TN5
U5U
UPT
VH1
WUQ
XPP
ZMT
~02
~G-
9DU
AAYXX
ACLOT
CITATION
EFKBS
EFLBG
~HD
ID FETCH-LOGICAL-c319t-43a2399d5dcafd48a2cde675fe842653b5d31ab5d3a9f801f10b0ad3848b7e2f3
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001500421100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0305-0548
IngestDate Sat Nov 29 07:45:27 EST 2025
Sat Jul 05 17:11:03 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Traveling salesman problem
Deep neural networks
Neural Combinatorial Optimization
Reinforcement learning
Language English
License This is an open access article under the CC BY license.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c319t-43a2399d5dcafd48a2cde675fe842653b5d31ab5d3a9f801f10b0ad3848b7e2f3
ORCID 0000-0002-3524-1600
0000-0002-8893-5227
0000-0002-8825-7817
OpenAccessLink https://dx.doi.org/10.1016/j.cor.2025.107102
ParticipantIDs crossref_primary_10_1016_j_cor_2025_107102
elsevier_sciencedirect_doi_10_1016_j_cor_2025_107102
PublicationCentury 2000
PublicationDate 2025-10-01
PublicationDateYYYYMMDD 2025-10-01
PublicationDate_xml – month: 10
  year: 2025
  text: 2025-10-01
  day: 01
PublicationDecade 2020
PublicationTitle Computers & operations research
PublicationYear 2025
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Bello, I., Pham, H., Le, Q.V., Norouzi, M., Bengio, S., 2017. Neural Combinatorial Optimization with Reinforcement Learning. In: 5th International Conference on Learning Representations, ICLR 2017.
Rumelhart, Hinton, Williams (b47) 1986; 323
Zhang, R., Prokhorchuk, A., Dauwels, J., 2020. Deep Reinforcement Learning for Traveling Salesman Problem with Time Windows and Rejections. In: 2020 International Joint Conference on Neural Networks. IJCNN, pp. 1–8.
Luo, Li, Fan, Liu (b34) 2022; 112
Weng, Chen, Yan, You, Duburcq, Zhang, Su, Su, Zhu (b58) 2022; 23
Cho, K., van Merriënboer, B., Gul̇çehre, Ç., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y., 2014. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. EMNLP, pp. 1724–1734.
Dai, Khalil, Zhang, Dilkina, Song (b11) 2017; 2017
Kwon, Choo, Kim, Yoon, Gwon, Min (b30) 2020; 33
Mirhoseini, Goldie, Yazgan, Jiang, Songhori, Wang, Lee, Johnson, Pathak, Nazi, Pak, Tong, Srinivasa, Hang, Tuncer, Le, Laudon, Ho, Carpenter, Dean (b37) 2021; 594
Powell (b43) 2022
Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., Long, M., 2023. TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. In: International Conference on Learning Representations.
Xin, Song, Cao, Zhang (b60) 2020; 17
Lin, Ghaddar, Nathwani (b31) 2022; 23
Peng, Wang, Zhang (b42) 2020
Paszke, Gross, Massa, Lerer, Bradbury, Chanan, Killeen, Lin, Gimelshein, Antiga (b41) 2019; 32
Joshi, Cappart, Rousseau, Laurent (b26) 2022; 27
Sutton, Barto (b53) 2018
Mazyavkina, Sviridov, Ivanov, Burnaev (b36) 2021; 134
Gupta, Gasse, Khalil, Kumar, Lodi, Bengio (b20) 2020; 2020
Bi, Ma, Zhou, Song, Cao, Wu, Zhang (b8) 2024; Vol. 37
Deudon, M., Cournut, P., Lacoste, A., Adulyasak, Y., Rousseau, L.-M., 2018. Learning heuristics for the tsp by policy gradient. In: Integration of Constraint Programming, Artificial Intelligence, and Operations Research: 15th International Conference. Vol. 15, pp. 170–181.
Nazari, Oroojlooy, Snyder, Takac (b40) 2018; 31
Berner, Brockman, Chan, Cheung, Dębiak, Dennison, Farhi, Fischer, Hashme, Hesse (b6) 2019
Berto, Hua, Zepeda, Hottung, Wouda, Lan, Tierney, Park (b7) 2024
Altman (b1) 2021
Jacobs, T., Alesiani, F., Ermis, G., 2021. Reinforcement Learning for Route Optimization with Robustness Guarantees. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. pp. 2592–2598.
Mnih, Badia, Mirza, Graves, Harley, Lillicrap, Silver, Kavukcuoglu (b38) 2016
Scarselli, Gori, Tsoi, Hagenbuchner, Monfardini (b48) 2009; 20
Battaglia, Hamrick, Bapst, Sanchez-Gonzalez, Zambaldi, Malinowski, Tacchetti, Raposo, Santoro, Faulkner, Gülçehre, Song, Ballard, Gilmer, Dahl, Vaswani, Allen, Nash, Langston, Dyer, Heess, Wierstra, Kohli, Botvinick, Vinyals, Li, Pascanu (b3) 2018
He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 770–778.
Puterman (b44) 2014
Zhao, Mao, Zhao, Zou (b63) 2021; 22
Bengio, Lodi, Prouvost (b5) 2021; 290
Rosenblatt (b46) 1958; 65 6
Towers, Terry, Kwiatkowski, Balis, Cola, Deleu, Goulão, Kallinteris, KG, Krimmel, Perez-Vicente, Pierré, Schulhoff, Tai, Shen, Younis (b54) 2023
Vesselinova, Steinert, Perez-Ramirez, Boman (b56) 2020; 8
Kool, W., Hoof, H.V., Welling, M., 2019. Attention, learn to solve routing problems!. In: 7th International Conference on Learning Representations, ICLR 2019.
Kaufmann, Bauersfeld, Loquercio, Müller, Koltun, Scaramuzza (b27) 2023; 620
Elsken, Metzen, Hutter (b15) 2019; 20
Liu, Zhang, Tang, Yao (b32) 2023; 18
Mnih, Kavukcuoglu, Silver, Rusu, Veness, Bellemare, Graves, Riedmiller, Fidjeland, Ostrovski, Petersen, Beattie, Sadik, Antonoglou, King, Kumaran, Wierstra, Legg, Hassabis (b39) 2015; 518
Bradbury, Frostig, Hawkins, Johnson, Leary, Maclaurin, Necula, Paszke, VanderPlas, Wanderman-Milne, Zhang (b9) 2018
Schrittwieser, Antonoglou, Hubert, Simonyan, Sifre, Schmitt, Guez, Lockhart, Hassabis, Graepel (b49) 2020; 588
Iklassov, Sobirov, Solozabal, Takáč (b24) 2024; vol. 222
Schulman, Wolski, Dhariwal, Radford, Klimov (b50) 2017
Fawzi, Balog, Huang, Hubert, Romera-Paredes, Barekatain, Novikov, Ruiz, Schrittwieser, Swirszcz, Silver, Hassabis, Kohli (b16) 2022; 610
Goodfellow, Bengio, Courville (b19) 2016
Hochreiter, Schmidhuber (b22) 1997; 9
Lodi, Zarpellon (b33) 2017; 25
Drori, I., Kharkar, A., Sickinger, W.R., Kates, B., Ma, Q., Ge, S., Dolev, E., Dietrich, B.L., Williamson, D.P., Udell, M., 2020. Learning to Solve Combinatorial Optimization Problems on Real-World Graphs in Linear Time. In: 2020 19th IEEE International Conference on Machine Learning and Applications. ICMLA, pp. 19–24.
Fu, Qiu, Zha (b17) 2021; 35
Luo, Lin, Liu, Zhang, Wang (b35) 2024; 36
Son, J., Kim, M., Kim, H., Park, J., 2023. Meta-SAGE: scale meta-learning scheduled adaptation with guided exploration for mitigating scale shift on combinatorial optimization. In: International Conference on Machine Learning. pp. 32194–32210.
Hopfield (b23) 1982; 79
Ye, Wang, Cao, Liang, Li (b61) 2023
Gilmer, Schoenholz, Riley, Vinyals, Dahl (b18) 2017
Kim, Park, Park (b28) 2022; 35
Raffin, Hill, Gleave, Kanervisto, Ernestus, Dormann (b45) 2021; 22
Drakulic, Michel, Mai, Sors, Andreoli (b13) 2023; Vol. 36
Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M., 2014. Deterministic policy gradient algorithms. In: International Conference on Machine Learning. pp. 387–395.
Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (b55) 2017; 30
Vinyals, Fortunato, Jaitly (b57) 2015; 28
Angioni, Belotti, Can Malli, Milesi (b2) 2023
Goodfellow (10.1016/j.cor.2025.107102_b19) 2016
Paszke (10.1016/j.cor.2025.107102_b41) 2019; 32
Gupta (10.1016/j.cor.2025.107102_b20) 2020; 2020
Hopfield (10.1016/j.cor.2025.107102_b23) 1982; 79
Berto (10.1016/j.cor.2025.107102_b7) 2024
Zhao (10.1016/j.cor.2025.107102_b63) 2021; 22
Nazari (10.1016/j.cor.2025.107102_b40) 2018; 31
Mnih (10.1016/j.cor.2025.107102_b38) 2016
Vesselinova (10.1016/j.cor.2025.107102_b56) 2020; 8
Drakulic (10.1016/j.cor.2025.107102_b13) 2023; Vol. 36
Raffin (10.1016/j.cor.2025.107102_b45) 2021; 22
Scarselli (10.1016/j.cor.2025.107102_b48) 2009; 20
Kwon (10.1016/j.cor.2025.107102_b30) 2020; 33
Liu (10.1016/j.cor.2025.107102_b32) 2023; 18
Sutton (10.1016/j.cor.2025.107102_b53) 2018
Xin (10.1016/j.cor.2025.107102_b60) 2020; 17
Kim (10.1016/j.cor.2025.107102_b28) 2022; 35
Bradbury (10.1016/j.cor.2025.107102_b9) 2018
Mazyavkina (10.1016/j.cor.2025.107102_b36) 2021; 134
Mnih (10.1016/j.cor.2025.107102_b39) 2015; 518
Hochreiter (10.1016/j.cor.2025.107102_b22) 1997; 9
Iklassov (10.1016/j.cor.2025.107102_b24) 2024; vol. 222
10.1016/j.cor.2025.107102_b51
10.1016/j.cor.2025.107102_b52
Vaswani (10.1016/j.cor.2025.107102_b55) 2017; 30
10.1016/j.cor.2025.107102_b10
Elsken (10.1016/j.cor.2025.107102_b15) 2019; 20
10.1016/j.cor.2025.107102_b12
10.1016/j.cor.2025.107102_b14
10.1016/j.cor.2025.107102_b59
Puterman (10.1016/j.cor.2025.107102_b44) 2014
Schulman (10.1016/j.cor.2025.107102_b50) 2017
Ye (10.1016/j.cor.2025.107102_b61) 2023
Peng (10.1016/j.cor.2025.107102_b42) 2020
Joshi (10.1016/j.cor.2025.107102_b26) 2022; 27
Rumelhart (10.1016/j.cor.2025.107102_b47) 1986; 323
Weng (10.1016/j.cor.2025.107102_b58) 2022; 23
Lodi (10.1016/j.cor.2025.107102_b33) 2017; 25
Battaglia (10.1016/j.cor.2025.107102_b3) 2018
10.1016/j.cor.2025.107102_b4
Mirhoseini (10.1016/j.cor.2025.107102_b37) 2021; 594
Fu (10.1016/j.cor.2025.107102_b17) 2021; 35
Luo (10.1016/j.cor.2025.107102_b35) 2024; 36
Dai (10.1016/j.cor.2025.107102_b11) 2017; 2017
Fawzi (10.1016/j.cor.2025.107102_b16) 2022; 610
10.1016/j.cor.2025.107102_b62
Gilmer (10.1016/j.cor.2025.107102_b18) 2017
Kaufmann (10.1016/j.cor.2025.107102_b27) 2023; 620
10.1016/j.cor.2025.107102_b21
Rosenblatt (10.1016/j.cor.2025.107102_b46) 1958; 65 6
Powell (10.1016/j.cor.2025.107102_b43) 2022
10.1016/j.cor.2025.107102_b25
10.1016/j.cor.2025.107102_b29
Lin (10.1016/j.cor.2025.107102_b31) 2022; 23
Bengio (10.1016/j.cor.2025.107102_b5) 2021; 290
Bi (10.1016/j.cor.2025.107102_b8) 2024; Vol. 37
Vinyals (10.1016/j.cor.2025.107102_b57) 2015; 28
Luo (10.1016/j.cor.2025.107102_b34) 2022; 112
Berner (10.1016/j.cor.2025.107102_b6) 2019
Angioni (10.1016/j.cor.2025.107102_b2) 2023
Altman (10.1016/j.cor.2025.107102_b1) 2021
Schrittwieser (10.1016/j.cor.2025.107102_b49) 2020; 588
Towers (10.1016/j.cor.2025.107102_b54) 2023
References_xml – volume: 518
  start-page: 529
  year: 2015
  end-page: 533
  ident: b39
  article-title: Human-level control through deep reinforcement learning
  publication-title: Nat.
– start-page: 1263
  year: 2017
  end-page: 1272
  ident: b18
  article-title: Neural message passing for Quantum chemistry
  publication-title: Proceedings of the 34th International Conference on Machine Learning - Volume 70
– volume: 2020
  start-page: 18087
  year: 2020
  end-page: 18097
  ident: b20
  article-title: Hybrid models for learning to branch
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 27
  start-page: 70
  year: 2022
  end-page: 98
  ident: b26
  article-title: Learning the travelling salesperson problem requires rethinking generalization
  publication-title: Constraints
– volume: 30
  year: 2017
  ident: b55
  article-title: Attention is all you need
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 22
  start-page: 7208
  year: 2021
  end-page: 7218
  ident: b63
  article-title: A hybrid of deep reinforcement learning and local search for the vehicle routing problems
  publication-title: IEEE Trans. Intell. Transp. Syst.
– reference: He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 770–778.
– volume: 65 6
  start-page: 386
  year: 1958
  end-page: 408
  ident: b46
  article-title: The perceptron: a probabilistic model for information storage and organization in the brain
  publication-title: Psychol Rev
– volume: 33
  start-page: 21188
  year: 2020
  end-page: 21198
  ident: b30
  article-title: POMO: Policy optimization with multiple optima for reinforcement learning
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 1928
  year: 2016
  end-page: 1937
  ident: b38
  article-title: Asynchronous methods for deep reinforcement learning
  publication-title: Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48
– volume: 23
  start-page: 1
  year: 2022
  end-page: 6
  ident: b58
  article-title: Tianshou: A highly modularized deep reinforcement learning library
  publication-title: J. Mach. Learn. Res.
– reference: Drori, I., Kharkar, A., Sickinger, W.R., Kates, B., Ma, Q., Ge, S., Dolev, E., Dietrich, B.L., Williamson, D.P., Udell, M., 2020. Learning to Solve Combinatorial Optimization Problems on Real-World Graphs in Linear Time. In: 2020 19th IEEE International Conference on Machine Learning and Applications. ICMLA, pp. 19–24.
– year: 2017
  ident: b50
  article-title: Proximal policy optimization algorithms
– volume: 35
  start-page: 7474
  year: 2021
  end-page: 7482
  ident: b17
  article-title: Generalize a small pre-trained model to arbitrarily large TSP instances
  publication-title: Proc. AAAI Conf. Artif. Intell.
– reference: Cho, K., van Merriënboer, B., Gul̇çehre, Ç., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y., 2014. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. EMNLP, pp. 1724–1734.
– volume: 620
  start-page: 982
  year: 2023
  end-page: 987
  ident: b27
  article-title: Champion-level drone racing using deep reinforcement learning
  publication-title: Nat.
– volume: 28
  year: 2015
  ident: b57
  article-title: Pointer networks
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 588
  start-page: 604
  year: 2020
  end-page: 609
  ident: b49
  article-title: Mastering atari, go, chess and shogi by planning with a learned model
  publication-title: Nat.
– volume: vol. 222
  start-page: 502
  year: 2024
  end-page: 517
  ident: b24
  article-title: Reinforcement learning for solving stochastic vehicle routing problem
  publication-title: Proceedings of the 15th Asian Conference on Machine Learning
– year: 2018
  ident: b3
  article-title: Relational inductive biases, deep learning, and graph networks
– volume: 32
  year: 2019
  ident: b41
  article-title: Pytorch: An imperative style, high-performance deep learning library
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 112
  year: 2022
  ident: b34
  article-title: A graph convolutional encoder and multi-head attention decoder network for TSP via reinforcement learning
  publication-title: Eng. Appl. Artif. Intell.
– volume: 290
  start-page: 405
  year: 2021
  end-page: 421
  ident: b5
  article-title: Machine learning for combinatorial optimization: a methodological tour d’horizon
  publication-title: European J. Oper. Res.
– start-page: 636
  year: 2020
  end-page: 650
  ident: b42
  article-title: A deep reinforcement learning algorithm using dynamic attention model for vehicle routing problems
  publication-title: Artificial Intelligence Algorithms and Applications: 11th International Symposium, ISICA 2019
– volume: 17
  start-page: 4861
  year: 2020
  end-page: 4871
  ident: b60
  article-title: Step-wise deep learning models for solving routing problems
  publication-title: IEEE Trans. Ind. Inform.
– volume: Vol. 37
  start-page: 93479
  year: 2024
  end-page: 93509
  ident: b8
  article-title: Learning to handle complex constraints for vehicle routing problems
  publication-title: Advances in Neural Information Processing Systems
– volume: 79
  start-page: 2554
  year: 1982
  end-page: 2558
  ident: b23
  article-title: Neural networks and physical systems with emergent collective computational abilities
  publication-title: Proc. Natl. Acad. Sci. USA
– reference: Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M., 2014. Deterministic policy gradient algorithms. In: International Conference on Machine Learning. pp. 387–395.
– year: 2024
  ident: b7
  article-title: RouteFinder: Towards foundation models for vehicle routing problems
  publication-title: ICML 2024 Workshop on Foundation Models in the Wild (Oral)
– volume: 2017
  start-page: 6349
  year: 2017
  end-page: 6359
  ident: b11
  article-title: Learning combinatorial optimization algorithms over graphs
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 22
  start-page: 1
  year: 2021
  end-page: 8
  ident: b45
  article-title: Stable-Baselines3: Reliable reinforcement learning implementations
  publication-title: J. Mach. Learn. Res.
– volume: 610
  start-page: 47
  year: 2022
  end-page: 53
  ident: b16
  article-title: Discovering faster matrix multiplication algorithms with reinforcement learning
  publication-title: Nat.
– volume: 8
  start-page: 120388
  year: 2020
  end-page: 120416
  ident: b56
  article-title: Learning combinatorial optimization on graphs: A survey with applications to networking
  publication-title: IEEE Access
– volume: Vol. 36
  start-page: 77416
  year: 2023
  end-page: 77429
  ident: b13
  article-title: BQ-NCO: Bisimulation quotienting for efficient neural combinatorial optimization
  publication-title: Advances in Neural Information Processing Systems
– volume: 134
  year: 2021
  ident: b36
  article-title: Reinforcement learning for combinatorial optimization: A survey
  publication-title: Comput. Oper. Res.
– volume: 31
  year: 2018
  ident: b40
  article-title: Reinforcement learning for solving the vehicle routing problem
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 35
  start-page: 1936
  year: 2022
  end-page: 1949
  ident: b28
  article-title: Sym-nco: Leveraging symmetricity for neural combinatorial optimization
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2023
  ident: b2
  article-title: SheepRL
– volume: 9
  start-page: 1735
  year: 1997
  end-page: 1780
  ident: b22
  article-title: Long short-term memory
  publication-title: Neural Comput.
– year: 2014
  ident: b44
  article-title: Markov decision processes: Discrete stochastic dynamic programming
  publication-title: Wiley Series in Probability and Statistics
– year: 2018
  ident: b9
  article-title: JAX: composable transformations of Python+NumPy programs
– reference: Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., Long, M., 2023. TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. In: International Conference on Learning Representations.
– volume: 20
  start-page: 1
  year: 2019
  end-page: 21
  ident: b15
  article-title: Neural architecture search: A survey
  publication-title: J. Mach. Learn. Res.
– reference: Zhang, R., Prokhorchuk, A., Dauwels, J., 2020. Deep Reinforcement Learning for Traveling Salesman Problem with Time Windows and Rejections. In: 2020 International Joint Conference on Neural Networks. IJCNN, pp. 1–8.
– reference: Son, J., Kim, M., Kim, H., Park, J., 2023. Meta-SAGE: scale meta-learning scheduled adaptation with guided exploration for mitigating scale shift on combinatorial optimization. In: International Conference on Machine Learning. pp. 32194–32210.
– year: 2023
  ident: b61
  article-title: DeepACO: Neural-enhanced ant systems for combinatorial optimization
  publication-title: Advances in Neural Information Processing Systems
– volume: 18
  start-page: 14
  year: 2023
  end-page: 28
  ident: b32
  article-title: How good is neural combinatorial optimization? A systematic evaluation on the traveling salesman problem
  publication-title: IEEE Comput. Intell. Mag.
– volume: 323
  start-page: 533
  year: 1986
  end-page: 536
  ident: b47
  article-title: Learning representations by back-propagating errors
  publication-title: Nat.
– volume: 20
  start-page: 61
  year: 2009
  end-page: 80
  ident: b48
  article-title: The graph neural network model
  publication-title: IEEE Trans. Neural Netw.
– year: 2023
  ident: b54
  article-title: Gymnasium
– volume: 36
  year: 2024
  ident: b35
  article-title: Neural combinatorial optimization with heavy decoder: Toward large scale generalization
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2018
  ident: b53
  article-title: Reinforcement Learning: An Introduction
– year: 2022
  ident: b43
  article-title: Reinforcement Learning and Stochastic Optimization: A Unified Framework for Sequential Decisions
– reference: Jacobs, T., Alesiani, F., Ermis, G., 2021. Reinforcement Learning for Route Optimization with Robustness Guarantees. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. pp. 2592–2598.
– volume: 25
  start-page: 207
  year: 2017
  end-page: 236
  ident: b33
  article-title: On learning and branching: A survey
  publication-title: Top
– volume: 23
  start-page: 11528
  year: 2022
  end-page: 11538
  ident: b31
  article-title: Deep reinforcement learning for the electric vehicle routing problem with time windows
  publication-title: IEEE Trans. Intell. Transp. Syst.
– year: 2019
  ident: b6
  article-title: Dota 2 with large scale deep reinforcement learning
– reference: Kool, W., Hoof, H.V., Welling, M., 2019. Attention, learn to solve routing problems!. In: 7th International Conference on Learning Representations, ICLR 2019.
– volume: 594
  start-page: 207
  year: 2021
  end-page: 212
  ident: b37
  article-title: A graph placement methodology for fast chip design
  publication-title: Nat.
– reference: Bello, I., Pham, H., Le, Q.V., Norouzi, M., Bengio, S., 2017. Neural Combinatorial Optimization with Reinforcement Learning. In: 5th International Conference on Learning Representations, ICLR 2017.
– reference: Deudon, M., Cournut, P., Lacoste, A., Adulyasak, Y., Rousseau, L.-M., 2018. Learning heuristics for the tsp by policy gradient. In: Integration of Constraint Programming, Artificial Intelligence, and Operations Research: 15th International Conference. Vol. 15, pp. 170–181.
– year: 2016
  ident: b19
  article-title: Deep Learning
– year: 2021
  ident: b1
  article-title: Constrained Markov Decision Processes
– year: 2023
  ident: 10.1016/j.cor.2025.107102_b2
– volume: 18
  start-page: 14
  year: 2023
  ident: 10.1016/j.cor.2025.107102_b32
  article-title: How good is neural combinatorial optimization? A systematic evaluation on the traveling salesman problem
  publication-title: IEEE Comput. Intell. Mag.
– volume: 594
  start-page: 207
  year: 2021
  ident: 10.1016/j.cor.2025.107102_b37
  article-title: A graph placement methodology for fast chip design
  publication-title: Nat.
  doi: 10.1038/s41586-021-03544-w
– ident: 10.1016/j.cor.2025.107102_b4
– year: 2018
  ident: 10.1016/j.cor.2025.107102_b53
– start-page: 636
  year: 2020
  ident: 10.1016/j.cor.2025.107102_b42
  article-title: A deep reinforcement learning algorithm using dynamic attention model for vehicle routing problems
– volume: 2020
  start-page: 18087
  year: 2020
  ident: 10.1016/j.cor.2025.107102_b20
  article-title: Hybrid models for learning to branch
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.cor.2025.107102_b29
– volume: 112
  year: 2022
  ident: 10.1016/j.cor.2025.107102_b34
  article-title: A graph convolutional encoder and multi-head attention decoder network for TSP via reinforcement learning
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2022.104848
– year: 2023
  ident: 10.1016/j.cor.2025.107102_b54
– volume: 22
  start-page: 7208
  year: 2021
  ident: 10.1016/j.cor.2025.107102_b63
  article-title: A hybrid of deep reinforcement learning and local search for the vehicle routing problems
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1109/TITS.2020.3003163
– volume: Vol. 36
  start-page: 77416
  year: 2023
  ident: 10.1016/j.cor.2025.107102_b13
  article-title: BQ-NCO: Bisimulation quotienting for efficient neural combinatorial optimization
– volume: vol. 222
  start-page: 502
  year: 2024
  ident: 10.1016/j.cor.2025.107102_b24
  article-title: Reinforcement learning for solving stochastic vehicle routing problem
– volume: Vol. 37
  start-page: 93479
  year: 2024
  ident: 10.1016/j.cor.2025.107102_b8
  article-title: Learning to handle complex constraints for vehicle routing problems
– volume: 27
  start-page: 70
  year: 2022
  ident: 10.1016/j.cor.2025.107102_b26
  article-title: Learning the travelling salesperson problem requires rethinking generalization
  publication-title: Constraints
  doi: 10.1007/s10601-022-09327-y
– volume: 620
  start-page: 982
  issue: 7976
  year: 2023
  ident: 10.1016/j.cor.2025.107102_b27
  article-title: Champion-level drone racing using deep reinforcement learning
  publication-title: Nat.
  doi: 10.1038/s41586-023-06419-4
– year: 2014
  ident: 10.1016/j.cor.2025.107102_b44
  article-title: Markov decision processes: Discrete stochastic dynamic programming
– ident: 10.1016/j.cor.2025.107102_b14
  doi: 10.1109/ICMLA51294.2020.00013
– ident: 10.1016/j.cor.2025.107102_b59
– volume: 610
  start-page: 47
  year: 2022
  ident: 10.1016/j.cor.2025.107102_b16
  article-title: Discovering faster matrix multiplication algorithms with reinforcement learning
  publication-title: Nat.
  doi: 10.1038/s41586-022-05172-4
– ident: 10.1016/j.cor.2025.107102_b21
  doi: 10.1109/CVPR.2016.90
– ident: 10.1016/j.cor.2025.107102_b62
  doi: 10.1109/IJCNN48605.2020.9207026
– volume: 79
  start-page: 2554
  issue: 8
  year: 1982
  ident: 10.1016/j.cor.2025.107102_b23
  article-title: Neural networks and physical systems with emergent collective computational abilities
  publication-title: Proc. Natl. Acad. Sci. USA
  doi: 10.1073/pnas.79.8.2554
– year: 2021
  ident: 10.1016/j.cor.2025.107102_b1
– volume: 518
  start-page: 529
  year: 2015
  ident: 10.1016/j.cor.2025.107102_b39
  article-title: Human-level control through deep reinforcement learning
  publication-title: Nat.
  doi: 10.1038/nature14236
– ident: 10.1016/j.cor.2025.107102_b25
  doi: 10.24963/ijcai.2021/357
– volume: 323
  start-page: 533
  year: 1986
  ident: 10.1016/j.cor.2025.107102_b47
  article-title: Learning representations by back-propagating errors
  publication-title: Nat.
  doi: 10.1038/323533a0
– volume: 31
  year: 2018
  ident: 10.1016/j.cor.2025.107102_b40
  article-title: Reinforcement learning for solving the vehicle routing problem
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 588
  start-page: 604
  year: 2020
  ident: 10.1016/j.cor.2025.107102_b49
  article-title: Mastering atari, go, chess and shogi by planning with a learned model
  publication-title: Nat.
  doi: 10.1038/s41586-020-03051-4
– volume: 28
  year: 2015
  ident: 10.1016/j.cor.2025.107102_b57
  article-title: Pointer networks
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2016
  ident: 10.1016/j.cor.2025.107102_b19
– volume: 65 6
  start-page: 386
  year: 1958
  ident: 10.1016/j.cor.2025.107102_b46
  article-title: The perceptron: a probabilistic model for information storage and organization in the brain
  publication-title: Psychol Rev
  doi: 10.1037/h0042519
– ident: 10.1016/j.cor.2025.107102_b12
  doi: 10.1007/978-3-319-93031-2_12
– year: 2019
  ident: 10.1016/j.cor.2025.107102_b6
– ident: 10.1016/j.cor.2025.107102_b51
– volume: 134
  year: 2021
  ident: 10.1016/j.cor.2025.107102_b36
  article-title: Reinforcement learning for combinatorial optimization: A survey
  publication-title: Comput. Oper. Res.
  doi: 10.1016/j.cor.2021.105400
– year: 2024
  ident: 10.1016/j.cor.2025.107102_b7
  article-title: RouteFinder: Towards foundation models for vehicle routing problems
– volume: 9
  start-page: 1735
  year: 1997
  ident: 10.1016/j.cor.2025.107102_b22
  article-title: Long short-term memory
  publication-title: Neural Comput.
  doi: 10.1162/neco.1997.9.8.1735
– volume: 2017
  start-page: 6349
  year: 2017
  ident: 10.1016/j.cor.2025.107102_b11
  article-title: Learning combinatorial optimization algorithms over graphs
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 23
  start-page: 1
  year: 2022
  ident: 10.1016/j.cor.2025.107102_b58
  article-title: Tianshou: A highly modularized deep reinforcement learning library
  publication-title: J. Mach. Learn. Res.
– volume: 35
  start-page: 1936
  year: 2022
  ident: 10.1016/j.cor.2025.107102_b28
  article-title: Sym-nco: Leveraging symmetricity for neural combinatorial optimization
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 30
  year: 2017
  ident: 10.1016/j.cor.2025.107102_b55
  article-title: Attention is all you need
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 290
  start-page: 405
  year: 2021
  ident: 10.1016/j.cor.2025.107102_b5
  article-title: Machine learning for combinatorial optimization: a methodological tour d’horizon
  publication-title: European J. Oper. Res.
  doi: 10.1016/j.ejor.2020.07.063
– volume: 20
  start-page: 1
  issue: 55
  year: 2019
  ident: 10.1016/j.cor.2025.107102_b15
  article-title: Neural architecture search: A survey
  publication-title: J. Mach. Learn. Res.
– volume: 25
  start-page: 207
  year: 2017
  ident: 10.1016/j.cor.2025.107102_b33
  article-title: On learning and branching: A survey
  publication-title: Top
  doi: 10.1007/s11750-017-0451-6
– start-page: 1928
  year: 2016
  ident: 10.1016/j.cor.2025.107102_b38
  article-title: Asynchronous methods for deep reinforcement learning
– volume: 20
  start-page: 61
  year: 2009
  ident: 10.1016/j.cor.2025.107102_b48
  article-title: The graph neural network model
  publication-title: IEEE Trans. Neural Netw.
  doi: 10.1109/TNN.2008.2005605
– ident: 10.1016/j.cor.2025.107102_b52
– year: 2017
  ident: 10.1016/j.cor.2025.107102_b50
– volume: 17
  start-page: 4861
  year: 2020
  ident: 10.1016/j.cor.2025.107102_b60
  article-title: Step-wise deep learning models for solving routing problems
  publication-title: IEEE Trans. Ind. Inform.
  doi: 10.1109/TII.2020.3031409
– volume: 36
  year: 2024
  ident: 10.1016/j.cor.2025.107102_b35
  article-title: Neural combinatorial optimization with heavy decoder: Toward large scale generalization
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 33
  start-page: 21188
  year: 2020
  ident: 10.1016/j.cor.2025.107102_b30
  article-title: POMO: Policy optimization with multiple optima for reinforcement learning
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 1263
  year: 2017
  ident: 10.1016/j.cor.2025.107102_b18
  article-title: Neural message passing for Quantum chemistry
– volume: 35
  start-page: 7474
  issue: 8
  year: 2021
  ident: 10.1016/j.cor.2025.107102_b17
  article-title: Generalize a small pre-trained model to arbitrarily large TSP instances
  publication-title: Proc. AAAI Conf. Artif. Intell.
– volume: 23
  start-page: 11528
  year: 2022
  ident: 10.1016/j.cor.2025.107102_b31
  article-title: Deep reinforcement learning for the electric vehicle routing problem with time windows
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1109/TITS.2021.3105232
– volume: 32
  year: 2019
  ident: 10.1016/j.cor.2025.107102_b41
  article-title: Pytorch: An imperative style, high-performance deep learning library
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.cor.2025.107102_b10
  doi: 10.3115/v1/D14-1179
– year: 2022
  ident: 10.1016/j.cor.2025.107102_b43
– year: 2018
  ident: 10.1016/j.cor.2025.107102_b9
– volume: 22
  start-page: 1
  year: 2021
  ident: 10.1016/j.cor.2025.107102_b45
  article-title: Stable-Baselines3: Reliable reinforcement learning implementations
  publication-title: J. Mach. Learn. Res.
– year: 2023
  ident: 10.1016/j.cor.2025.107102_b61
  article-title: DeepACO: Neural-enhanced ant systems for combinatorial optimization
– year: 2018
  ident: 10.1016/j.cor.2025.107102_b3
– volume: 8
  start-page: 120388
  year: 2020
  ident: 10.1016/j.cor.2025.107102_b56
  article-title: Learning combinatorial optimization on graphs: A survey with applications to networking
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.3004964
SSID ssj0000721
Score 2.4684384
Snippet Recent advancements in deep reinforcement learning have sparked a growing interest in the application of this approach to solve combinatorial optimization (CO)...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 107102
SubjectTerms Deep neural networks
Neural Combinatorial Optimization
Reinforcement learning
Traveling salesman problem
Title Neural combinatorial optimization: A tutorial
URI https://dx.doi.org/10.1016/j.cor.2025.107102
Volume 182
WOSCitedRecordID wos001500421100001&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: 0305-0548
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0000721
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3da9swED-6pIzuoR_Zyvo1_NCnDhd_qZL7Fkq_Bi2FpJA3I8sypKxOSJxR-tfvZEm2W1JYB30RRsYXcz_l7nfy3QngkEQYNAhfuOgLMUAJqOcy9HNuiFTX4x6VRLLqsAl6e8tGo_jOHCU3r44ToEXBnp7i6YdCjXMItiqdfQfctVCcwGsEHUeEHcd_Al6126iafjxi0KtCarUnPkHL8GhKLnUxernQt9rs1B7xMK8WxGQqZyZRzrQEqreO-4VKYx7XSfGtdYOLoNQpAme_-SIb12Z_oMQVzxVZvTn-eTnjz-am2XQISJ2-ZnbCbDVMk3pUVWCpRECiO2c21jVYaqn1psEDKlp1ZQ0Iziiy07ilOllwoOQqscjW1HfW8BN0A0pi1oFu__p89KvxvLSqs6vfw37FrvL5Xv3Qch7S4hbDTVg3QYHT12BuwYosevDZ1iT0YMMC4xhT3IMvrUaSX8HVoDsvQHfaoJ86fcdC_g3uL86HZ1euOQjDFWghSzcKuSpBzkgmeJ5FjAcikxjp5ZIhwSJhSrLQ52rkcY6UI_e91ONZyCKWUhnk4TZ0ikkhv4NDSXDC0cn5IiVRLAUP00ikFP-tKNA_8XbgyKolmep-J4lNBHxIUIeJ0mGidbgDkVVcYgibJmIJovz2Y7v_99gerDVLcR865WwhD2BV_CnH89kPsxb-AvnEYZ8
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=Neural+combinatorial+optimization%3A+A+tutorial&rft.jtitle=Computers+%26+operations+research&rft.au=Angioni%2C+Davide&rft.au=Archetti%2C+Claudia&rft.au=Speranza%2C+M.+Grazia&rft.date=2025-10-01&rft.pub=Elsevier+Ltd&rft.issn=0305-0548&rft.volume=182&rft_id=info:doi/10.1016%2Fj.cor.2025.107102&rft.externalDocID=S0305054825001303
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0305-0548&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0305-0548&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0305-0548&client=summon