Reinforcement learning for search tree size minimization in Constraint Programming: New results on scheduling benchmarks

Failure-Directed Search (FDS) is a significant complete generic search algorithm used in Constraint Programming (CP) to efficiently explore the search space, proven particularly effective on scheduling problems. This paper analyzes FDS’s properties, showing that minimizing the size of its search tre...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computers & industrial engineering Jg. 209; S. 111413
Hauptverfasser: Heinz, Vilém, Vilím, Petr, Hanzálek, Zdeněk
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.11.2025
Schlagworte:
ISSN:0360-8352
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Failure-Directed Search (FDS) is a significant complete generic search algorithm used in Constraint Programming (CP) to efficiently explore the search space, proven particularly effective on scheduling problems. This paper analyzes FDS’s properties, showing that minimizing the size of its search tree guided by ranked branching decisions is closely related to the Multi-armed bandit (MAB) problem. Building on this insight, MAB reinforcement learning algorithms are applied to FDS, extended with problem-specific refinements and parameter tuning, and evaluated on the two most fundamental scheduling problems, the Job Shop Scheduling Problem (JSSP) and Resource-Constrained Project Scheduling Problem (RCPSP). The resulting enhanced FDS, using the best extended MAB algorithm and configuration, performs 1.7 times faster on the JSSP and 2.5 times faster on the RCPSP benchmarks compared to the original implementation in a new solver called OptalCP, while also being 3.5 times faster on the JSSP and 2.1 times faster on the RCPSP benchmarks than the current state-of-the-art FDS algorithm in IBM CP Optimizer 22.1. Furthermore, using only a 900s time limit per instance, the enhanced FDS improved the existing state-of-the-art lower bounds of 78 of 84 JSSP and 226 of 393 RCPSP standard open benchmark instances while also completely closing a few of them. •Reinforcement learning strongly improves Failure-Directed Search (FDS) efficiency.•FDS parameter tuning yields noticeable improvement and insight into their importance.•Two-fold improvement over baseline FDS achieved on fundamental scheduling problems.•Even larger improvement is achieved over state-of-the-art CP Optimizer’s FDS.•Hundreds of improved lower bounds for famous JSSP and RCPSP instances were obtained.
AbstractList Failure-Directed Search (FDS) is a significant complete generic search algorithm used in Constraint Programming (CP) to efficiently explore the search space, proven particularly effective on scheduling problems. This paper analyzes FDS’s properties, showing that minimizing the size of its search tree guided by ranked branching decisions is closely related to the Multi-armed bandit (MAB) problem. Building on this insight, MAB reinforcement learning algorithms are applied to FDS, extended with problem-specific refinements and parameter tuning, and evaluated on the two most fundamental scheduling problems, the Job Shop Scheduling Problem (JSSP) and Resource-Constrained Project Scheduling Problem (RCPSP). The resulting enhanced FDS, using the best extended MAB algorithm and configuration, performs 1.7 times faster on the JSSP and 2.5 times faster on the RCPSP benchmarks compared to the original implementation in a new solver called OptalCP, while also being 3.5 times faster on the JSSP and 2.1 times faster on the RCPSP benchmarks than the current state-of-the-art FDS algorithm in IBM CP Optimizer 22.1. Furthermore, using only a 900s time limit per instance, the enhanced FDS improved the existing state-of-the-art lower bounds of 78 of 84 JSSP and 226 of 393 RCPSP standard open benchmark instances while also completely closing a few of them. •Reinforcement learning strongly improves Failure-Directed Search (FDS) efficiency.•FDS parameter tuning yields noticeable improvement and insight into their importance.•Two-fold improvement over baseline FDS achieved on fundamental scheduling problems.•Even larger improvement is achieved over state-of-the-art CP Optimizer’s FDS.•Hundreds of improved lower bounds for famous JSSP and RCPSP instances were obtained.
ArticleNumber 111413
Author Hanzálek, Zdeněk
Vilím, Petr
Heinz, Vilém
Author_xml – sequence: 1
  givenname: Vilém
  orcidid: 0000-0001-6051-6699
  surname: Heinz
  fullname: Heinz, Vilém
  email: vilem.heinz@cvut.cz
  organization: Faculty of Electrical Engineering, Czech Technical University in Prague, Czech Republic
– sequence: 2
  givenname: Petr
  surname: Vilím
  fullname: Vilím, Petr
  organization: ScheduleOpt, Czech Republic
– sequence: 3
  givenname: Zdeněk
  orcidid: 0000-0002-8135-1296
  surname: Hanzálek
  fullname: Hanzálek, Zdeněk
  organization: Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, Czech Republic
BookMark eNp9kFtLAzEQhfNQwVb9Ab7lD-yabDZ70Scp3qCoiD6HdHbSpu4mkmy99NebUp-FgWGGcw6Hb0Ymzjsk5JyznDNeXWxysJgXrJA557zkYkKmTFQsa4Qsjsksxg1jrJQtn5LvF7TO-AA4oBtpjzo461Y0vWhMB6zpGBBptDukg3V2sDs9Wu-odXTuXRyDtsn4HPwq6CEpVpf0Eb9owLjtx0iTMsIau22_j12ig_Wgw3s8JUdG9xHP_vYJebu9eZ3fZ4unu4f59SKDgrUik0zWrRDSlAVnUMllWYnKtMCbAkxVg-6MNI1gjUSpG9RNB1UDRZpWyBpqcUL4IReCjzGgUR_BpgY_ijO1x6U2KuFSe1zqgCt5rg4eTMU-LQYVk8QBdjYgjKrz9h_3L1k9eLc
Cites_doi 10.1016/j.orl.2004.04.002
10.1145/378239.379017
10.1016/S0377-2217(98)00364-6
10.1609/aaai.v32i1.12211
10.1287/mnsc.34.3.391
10.1016/j.ijpe.2023.108958
10.1016/j.cor.2024.106964
10.1016/S0377-2217(97)00019-2
10.1016/j.ejor.2022.11.034
10.1609/aaai.v37i10.26466
10.1287/mnsc.38.10.1495
10.1007/s10844-021-00666-5
10.13164/mendel.2020.2.009
10.1609/aaai.v35i5.16512
10.1145/3292500.3330701
10.1016/j.omega.2022.102770
10.1609/aaai.v30i1.10080
10.1016/S0377-2217(96)00170-1
10.1016/0377-2217(93)90182-M
10.1023/A:1006314320276
10.1287/ijoc.2023.1287
10.1090/S0002-9904-1952-09620-8
10.1016/j.cor.2020.104976
10.1002/1099-1425(200101/02)4:1<53::AID-JOS59>3.0.CO;2-Y
10.1016/j.cie.2022.108128
10.1609/aaai.v39i11.33239
10.1016/j.cie.2020.106857
10.1016/j.cor.2012.04.018
10.1016/j.cor.2020.105020
10.1016/j.artint.2009.09.002
10.1016/j.cie.2022.108586
ContentType Journal Article
Copyright 2025 The Authors
Copyright_xml – notice: 2025 The Authors
DBID 6I.
AAFTH
AAYXX
CITATION
DOI 10.1016/j.cie.2025.111413
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Engineering
ExternalDocumentID 10_1016_j_cie_2025_111413
S0360835225005595
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
1B1
1RT
1~.
1~5
29F
4.4
457
4G.
5GY
5VS
6I.
7-5
71M
8P~
9JN
9JO
AAAKG
AABNK
AAEDT
AAEDW
AAFTH
AAFWJ
AAIKC
AAIKJ
AAKOC
AALRI
AAMNW
AAOAW
AAQFI
AAQXK
AARIN
AATTM
AAXKI
AAXUO
AAYWO
ABAOU
ABDPE
ABJNI
ABMAC
ABUCO
ABWVN
ABXDB
ACDAQ
ACGFO
ACGFS
ACLOT
ACNCT
ACNNM
ACRLP
ACRPL
ACVFH
ADBBV
ADCNI
ADEZE
ADGUI
ADMUD
ADNMO
ADRHT
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFTJW
AGHFR
AGQPQ
AGUBO
AGYEJ
AHHHB
AHJVU
AIEXJ
AIGII
AIGVJ
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
APLSM
APXCP
ARUGR
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BKOMP
BLXMC
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
HAMUX
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
LX9
LY1
LY7
M41
MHUIS
MO0
MS~
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
R2-
RNS
ROL
RPZ
RXW
SBC
SDF
SDG
SDP
SDS
SES
SET
SEW
SPC
SPCBC
SSB
SSD
SST
SSW
SSZ
T5K
TAE
TN5
WUQ
XPP
ZMT
~G-
~HD
9DU
AAYXX
CITATION
ID FETCH-LOGICAL-c2093-50579335f4210c65b4636f9c182cf67cadf5f83085e5a8ea8dc68c28c29357c73
ISSN 0360-8352
IngestDate Sat Nov 29 07:05:04 EST 2025
Sat Nov 15 16:53:10 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords 68T20
90C99
Heuristics
90-08
90B35
Reinforcement learning
Discrete optimization
90C59
Scheduling
90C27
Constraint Programming
Tree search
Language English
License This is an open access article under the CC BY license.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c2093-50579335f4210c65b4636f9c182cf67cadf5f83085e5a8ea8dc68c28c29357c73
ORCID 0000-0002-8135-1296
0000-0001-6051-6699
OpenAccessLink https://dx.doi.org/10.1016/j.cie.2025.111413
ParticipantIDs crossref_primary_10_1016_j_cie_2025_111413
elsevier_sciencedirect_doi_10_1016_j_cie_2025_111413
PublicationCentury 2000
PublicationDate November 2025
2025-11-00
PublicationDateYYYYMMDD 2025-11-01
PublicationDate_xml – month: 11
  year: 2025
  text: November 2025
PublicationDecade 2020
PublicationTitle Computers & industrial engineering
PublicationYear 2025
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Adams, Balas, Zawack (b3) 1988; 34
Xia, Yap (b66) 2018; 32
Boussemart, Hemery, Lecoutre, Sais (b9) 2004; vol. 16
Zarpellon, Jo, Lodi, Bengio (b70) 2021; 35
Michel, Hentenryck (b42) 2012
Jongejan (b27) 2023
Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019). Optuna: A Next-generation Hyperparameter Optimization Framework. In
Storer, Wu, Vaccari (b57) 1992; 38
Optimizizer (b47) 2023
Khalil, Le Bodic, Song, Nemhauser, Dilkina (b29) 2016; 30
Lecoutre, Sais, Tabary, Vidal (b36) 2007; vol. 7
Vilím (b62) 2012
Liang, Ganesh, Poupart, Czarnecki (b37) 2016
Bouška, Šůcha, Novák, Hanzálek (b8) 2023; 308
Chapelle, Li (b14) 2011; vol. 24
Habet, D., & Terrioux, C. (2018). Conflict History Based Branching Heuristic for CSP Solving. In
Vilím (b61) 2009
Bonfietti, Lombardi, Milano (b7) 2015
Balafrej, Bessiere, Paparrizou (b6) 2015
Refalo (b51) 2004
Popescu, Polat-Erdeniz, Felfernig, Uta, Atas, Le (b50) 2022; 58
Kletzander, Musliu (b30) 2023; 37
Wattez, Koriche, Lecoutre, Paparrizou, Tabary (b64) 2020; vol. 325
He, Qu (b24) 2012; 39
.
Chalumeau, Coulon, Cappart, Rousseau (b13) 2021
Kuleshov, Precup (b34) 2014
Vilím, Laborie, Shaw (b63) 2015
Demirkol, Mehta, Uzsoy (b16) 1998; 109
Heinz, Novák, Vlk, Hanzálek (b25) 2022; 172
Naderia, Ruizb, Roshanaeic (b44) 2023
Applegate, Bixby, Chvatal, Cook (b5) 1995
Achterberg, Koch, Martin (b2) 2005; 33
Yamada, Nakano (b68) 1992; vol. 2
Fatemi-Anaraki, Tavakkoli-Moghaddam, Foumani, Vahedi-Nouri (b18) 2023; 115
ScheduleOpt (b54) 2023
Hauder, Beham, Raggl, Parragh, Affenzeller (b23) 2020; 150
Wattez, Lecoutre, Paparrizou, Tabary (b65) 2019
Abreu, Nagano (b1) 2022; 168
ScheduleOpt (b55) 2025
Gomes, Selman, Crato, Kautz (b21) 2000; 24
(pp. 1–10). Volos, Greece: URL
Rohaninejad, Hanzálek (b53) 2023; 263
Kolisch, Sprecher (b31) 1997; 96
Doolaard, Yorke-Smith (b17) 2022
Optal (b46) 2023
Gay, Hartert, Schaus (b19) 2015
Nedbálek, Novák (b45) 2025
Koster, Beney (b33) 2007
Mahajan, Teneketzis (b41) 2008
Koriche, Lecoutre, Paparrizou, Wattez (b32) 2022
(pp. 1–10).
Sutton, Barto (b58) 2018
Loth, Sebag, Hamadi, Schoenauer (b39) 2013
University of Ghent (b60) 2023
Coelho, Vanhoucke (b15) 2020; 121
Brailsford, Potts, Smith (b10) 1999; 119
Brinkkötter, Brucker (b11) 2001; 4
Taillard (b59) 1993; 64
Godard, Laborie, Nuijten (b20) 2005; vol. 5
(pp. 530–535).
Kazikova, Pluhacek, Senkerik (b28) 2020; 26
Liess, Michelon (b38) 2008; 157
Xu, Wu, Li, Yin (b67) 2025; 39
IBM (b26) 2023
Moskewicz, M. W., Madigan, C. F., Zhao, Y., Zhang, L., & Malik, S. (2001). Chaff: Engineering an efficient SAT solver. In
Robbins (b52) 1952; 58
Ouellet, Quimper (b48) 2013
Shaw (b56) 1998
Philippe Baptiste (b49) 2012
Yuraszeck, Mejía, Rossit, Lüer-Villagra (b69) 2025; 177
Cappart, Moisan, Rousseau, Prémont-Schwarz, Cire (b12) 2020
Lunardi, Birgin, Laborie, Ronconi, Voos (b40) 2020; 123
Lecoutre, Saïs, Tabary, Vidal (b35) 2009; 173
Godard (10.1016/j.cie.2025.111413_b20) 2005; vol. 5
Refalo (10.1016/j.cie.2025.111413_b51) 2004
Doolaard (10.1016/j.cie.2025.111413_b17) 2022
Adams (10.1016/j.cie.2025.111413_b3) 1988; 34
Liang (10.1016/j.cie.2025.111413_b37) 2016
ScheduleOpt (10.1016/j.cie.2025.111413_b55) 2025
Yuraszeck (10.1016/j.cie.2025.111413_b69) 2025; 177
Yamada (10.1016/j.cie.2025.111413_b68) 1992; vol. 2
Lecoutre (10.1016/j.cie.2025.111413_b36) 2007; vol. 7
Demirkol (10.1016/j.cie.2025.111413_b16) 1998; 109
Loth (10.1016/j.cie.2025.111413_b39) 2013
Chapelle (10.1016/j.cie.2025.111413_b14) 2011; vol. 24
Bouška (10.1016/j.cie.2025.111413_b8) 2023; 308
Gay (10.1016/j.cie.2025.111413_b19) 2015
Mahajan (10.1016/j.cie.2025.111413_b41) 2008
ScheduleOpt (10.1016/j.cie.2025.111413_b54) 2023
Xu (10.1016/j.cie.2025.111413_b67) 2025; 39
Kazikova (10.1016/j.cie.2025.111413_b28) 2020; 26
Fatemi-Anaraki (10.1016/j.cie.2025.111413_b18) 2023; 115
Jongejan (10.1016/j.cie.2025.111413_b27) 2023
Lecoutre (10.1016/j.cie.2025.111413_b35) 2009; 173
Robbins (10.1016/j.cie.2025.111413_b52) 1952; 58
10.1016/j.cie.2025.111413_b22
Brailsford (10.1016/j.cie.2025.111413_b10) 1999; 119
Vilím (10.1016/j.cie.2025.111413_b63) 2015
Liess (10.1016/j.cie.2025.111413_b38) 2008; 157
Naderia (10.1016/j.cie.2025.111413_b44) 2023
Boussemart (10.1016/j.cie.2025.111413_b9) 2004; vol. 16
University of Ghent (10.1016/j.cie.2025.111413_b60) 2023
Xia (10.1016/j.cie.2025.111413_b66) 2018; 32
Gomes (10.1016/j.cie.2025.111413_b21) 2000; 24
Bonfietti (10.1016/j.cie.2025.111413_b7) 2015
Kolisch (10.1016/j.cie.2025.111413_b31) 1997; 96
Applegate (10.1016/j.cie.2025.111413_b5) 1995
He (10.1016/j.cie.2025.111413_b24) 2012; 39
Kuleshov (10.1016/j.cie.2025.111413_b34) 2014
Vilím (10.1016/j.cie.2025.111413_b62) 2012
Sutton (10.1016/j.cie.2025.111413_b58) 2018
Taillard (10.1016/j.cie.2025.111413_b59) 1993; 64
Wattez (10.1016/j.cie.2025.111413_b65) 2019
Brinkkötter (10.1016/j.cie.2025.111413_b11) 2001; 4
Kletzander (10.1016/j.cie.2025.111413_b30) 2023; 37
Wattez (10.1016/j.cie.2025.111413_b64) 2020; vol. 325
Ouellet (10.1016/j.cie.2025.111413_b48) 2013
Koriche (10.1016/j.cie.2025.111413_b32) 2022
Abreu (10.1016/j.cie.2025.111413_b1) 2022; 168
Coelho (10.1016/j.cie.2025.111413_b15) 2020; 121
10.1016/j.cie.2025.111413_b4
Vilím (10.1016/j.cie.2025.111413_b61) 2009
Nedbálek (10.1016/j.cie.2025.111413_b45) 2025
Optimizizer (10.1016/j.cie.2025.111413_b47) 2023
Heinz (10.1016/j.cie.2025.111413_b25) 2022; 172
Shaw (10.1016/j.cie.2025.111413_b56) 1998
Lunardi (10.1016/j.cie.2025.111413_b40) 2020; 123
Optal (10.1016/j.cie.2025.111413_b46) 2023
Storer (10.1016/j.cie.2025.111413_b57) 1992; 38
Koster (10.1016/j.cie.2025.111413_b33) 2007
Michel (10.1016/j.cie.2025.111413_b42) 2012
10.1016/j.cie.2025.111413_b43
Chalumeau (10.1016/j.cie.2025.111413_b13) 2021
Hauder (10.1016/j.cie.2025.111413_b23) 2020; 150
Balafrej (10.1016/j.cie.2025.111413_b6) 2015
Rohaninejad (10.1016/j.cie.2025.111413_b53) 2023; 263
Popescu (10.1016/j.cie.2025.111413_b50) 2022; 58
Philippe Baptiste (10.1016/j.cie.2025.111413_b49) 2012
Zarpellon (10.1016/j.cie.2025.111413_b70) 2021; 35
Cappart (10.1016/j.cie.2025.111413_b12) 2020
Khalil (10.1016/j.cie.2025.111413_b29) 2016; 30
Achterberg (10.1016/j.cie.2025.111413_b2) 2005; 33
IBM (10.1016/j.cie.2025.111413_b26) 2023
References_xml – volume: 115
  year: 2023
  ident: b18
  article-title: Scheduling of Multi-Robot job shop systems in dynamic environments: Mixed-Integer linear programming and constraint programming approaches
  publication-title: Omega
– year: 2023
  ident: b47
  article-title: Job shop scheduling problem solver
– volume: 58
  start-page: 527
  year: 1952
  end-page: 535
  ident: b52
  article-title: Some aspects of the sequential design of experiments
  publication-title: Bulletin of the American Mathematical Society
– year: 2012
  ident: b49
  article-title: Constraint-based scheduling applying constraint programming to scheduling problems
– volume: 263
  year: 2023
  ident: b53
  article-title: Multi-level lot-sizing and job shop scheduling with lot-streaming: Reformulation and solution approaches
  publication-title: International Journal of Production Economics
– start-page: 71
  year: 2019
  end-page: 77
  ident: b65
  article-title: Refining constraint weighting
  publication-title: 2019 IEEE 31st international conference on tools with artificial intelligence
– year: 2023
  ident: b46
  article-title: FDS experimental results
– volume: 37
  start-page: 12444
  year: 2023
  end-page: 12452
  ident: b30
  article-title: Large-State reinforcement learning for Hyper-Heuristics
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– reference: Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019). Optuna: A Next-generation Hyperparameter Optimization Framework. In
– volume: vol. 2
  start-page: 283
  year: 1992
  end-page: 292
  ident: b68
  article-title: A genetic algorithm applicable to large-scale job-shop problems
  publication-title: Parallel problem solving from nature 2
– volume: vol. 24
  start-page: 2249
  year: 2011
  end-page: 2257
  ident: b14
  article-title: An empirical evaluation of Thompson sampling
  publication-title: Advances in neural information processing systems
– year: 2023
  ident: b60
  article-title: Resource-Constrained project scheduling
– volume: 157
  year: 2008
  ident: b38
  article-title: A constraint programming approach for the resource-constrained project scheduling problem
  publication-title: Annals of Operations Research
– volume: 24
  start-page: 67
  year: 2000
  end-page: 100
  ident: b21
  article-title: Heavy-tailed phenomena in satisfiability and constraint satisfaction problems
  publication-title: Journal of Automated Reasoning
– year: 2025
  ident: b55
  article-title: OptalCP
– volume: 58
  start-page: 91
  year: 2022
  end-page: 118
  ident: b50
  article-title: An overview of machine learning techniques in constraint solving
  publication-title: Journal of Intelligent Information Systems
– year: 2023
  ident: b26
  article-title: CP Optimizer
– reference: Moskewicz, M. W., Madigan, C. F., Zhao, Y., Zhang, L., & Malik, S. (2001). Chaff: Engineering an efficient SAT solver. In
– volume: 33
  start-page: 42
  year: 2005
  end-page: 54
  ident: b2
  article-title: Branching rules revisited
  publication-title: Operations Research Letters
– year: 1995
  ident: b5
  article-title: Finding cuts in the TSP (A preliminary report)
– year: 2022
  ident: b17
  article-title: Online learning of variable ordering heuristics for constraint optimisation problems
  publication-title: Annals of Mathematics and Artificial Intelligence
– volume: 26
  start-page: 9
  year: 2020
  end-page: 16
  ident: b28
  article-title: Why tuning the control parameters of metaheuristic algorithms is so important for fair comparison?
  publication-title: Mendel
– volume: 32
  year: 2018
  ident: b66
  article-title: Learning robust search strategies using a Bandit-Based approach
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– volume: 172
  year: 2022
  ident: b25
  article-title: Constraint programming and constructive heuristics for parallel machine scheduling with sequence-dependent setups and common servers
  publication-title: Computers & Industrial Engineering
– volume: 34
  start-page: 391
  year: 1988
  end-page: 401
  ident: b3
  article-title: The shifting bottleneck procedure for job shop scheduling
  publication-title: Management Science
– start-page: 417
  year: 1998
  end-page: 431
  ident: b56
  article-title: Using constraint programming and local search methods to solve vehicle routing problems
  publication-title: International conference on principles and practice of constraint programming
– year: 2012
  ident: b62
  article-title: Global constraints in scheduling
– volume: 123
  year: 2020
  ident: b40
  article-title: Mixed integer linear programming and constraint programming models for the online printing shop scheduling problem
  publication-title: Computers & Operations Research
– reference: (pp. 1–10).
– year: 2023
  ident: b54
  article-title: Optalcp
– start-page: 464
  year: 2013
  end-page: 480
  ident: b39
  article-title: Bandit-based search for constraint programming
  publication-title: International conference on principles and practice of constraint programming
– volume: vol. 325
  start-page: 479
  year: 2020
  end-page: 486
  ident: b64
  article-title: Learning variable ordering heuristics with Multi-Armed bandits and restarts
  publication-title: ECAI 2020 - 24th European conference on artificial intelligence
– start-page: 74
  year: 2015
  end-page: 90
  ident: b7
  article-title: Embedding decision trees and random forests in constraint programming
  publication-title: Integration of AI and OR techniques in constraint programming
– volume: 119
  start-page: 557
  year: 1999
  end-page: 581
  ident: b10
  article-title: Constraint satisfaction problems: Algorithms and applications
  publication-title: European Journal of Operational Research
– start-page: 392
  year: 2021
  end-page: 409
  ident: b13
  article-title: SeaPearl: A constraint programming solver guided by reinforcement learning
  publication-title: Integration of constraint programming, artificial intelligence, and operations research
– volume: 168
  year: 2022
  ident: b1
  article-title: A new hybridization of adaptive large neighborhood search with constraint programming for open shop scheduling with sequence-dependent setup times
  publication-title: Computers & Industrial Engineering
– volume: 39
  start-page: 3331
  year: 2012
  end-page: 3343
  ident: b24
  article-title: A constraint programming based column generation approach to nurse rostering problems
  publication-title: Computers & Operations Research
– start-page: 121
  year: 2008
  end-page: 151
  ident: b41
  article-title: Multi-Armed Bandit problems
  publication-title: Foundations and applications of sensor management
– year: 2014
  ident: b34
  article-title: Algorithms for multi-armed bandit problems
– volume: 173
  start-page: 1592
  year: 2009
  end-page: 1614
  ident: b35
  article-title: Reasoning from last conflict(s) in constraint programming
  publication-title: Artificial Intelligence
– volume: 150
  year: 2020
  ident: b23
  article-title: Resource-constrained multi-project scheduling with activity and time flexibility
  publication-title: Computers & Industrial Engineering
– start-page: 123
  year: 2016
  end-page: 140
  ident: b37
  article-title: Learning rate based branching heuristic for SAT solvers
  publication-title: Theory and applications of satisfiability testing – SAT 2016
– reference: (pp. 1–10). Volos, Greece: URL
– volume: 38
  start-page: 1495
  year: 1992
  end-page: 1509
  ident: b57
  article-title: New search spaces for sequencing problems with application to job shop scheduling
  publication-title: Management Science
– volume: 30
  year: 2016
  ident: b29
  article-title: Learning to branch in mixed integer programming
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– volume: 121
  year: 2020
  ident: b15
  article-title: Going to the core of hard resource-constrained project scheduling instances
  publication-title: Computers & Operations Research
– volume: 109
  start-page: 137
  year: 1998
  end-page: 141
  ident: b16
  article-title: Benchmarks for shop scheduling problems
  publication-title: European Journal of Operational Research
– start-page: 437
  year: 2015
  end-page: 453
  ident: b63
  article-title: Failure-directed search for constraint-based scheduling
  publication-title: International conference on integration of constraint programming, artificial intelligence, and operations research
– start-page: 228
  year: 2012
  end-page: 243
  ident: b42
  article-title: Activity-based search for black-box constraint programming solvers
  publication-title: International conference on integration of artificial intelligence (AI) and operations research (OR) techniques in constraint programming
– year: 2023
  ident: b27
  article-title: Job shop problem solver
– start-page: 340
  year: 2025
  end-page: 347
  ident: b45
  article-title: Bottleneck identification in Resource-Constrained project scheduling via constraint relaxation
  publication-title: Proceedings of the 14th international conference on operations research and enterprise systems - ICORES
– year: 2023
  ident: b44
  article-title: Mixed-Integer programming versus constraint programming for shop scheduling problems: New results and outlook
  publication-title: INFORMS Journal on Computing
– reference: Habet, D., & Terrioux, C. (2018). Conflict History Based Branching Heuristic for CSP Solving. In
– volume: 35
  start-page: 3931
  year: 2021
  end-page: 3939
  ident: b70
  article-title: Parameterizing Branch-and-Bound search trees to learn branching policies
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– start-page: 557
  year: 2004
  end-page: 571
  ident: b51
  article-title: Impact-based search strategies for constraint programming
  publication-title: International conference on principles and practice of constraint programming
– volume: 96
  start-page: 205
  year: 1997
  end-page: 216
  ident: b31
  article-title: PSPLIB - a project scheduling problem library: OR software - orsep operations research software exchange program
  publication-title: European Journal of Operational Research
– start-page: 562
  year: 2013
  end-page: 577
  ident: b48
  article-title: Time-table extended-edge-finding for the cumulative constraint
  publication-title: Principles and practice of constraint programming
– volume: 39
  start-page: 11390
  year: 2025
  end-page: 11398
  ident: b67
  article-title: Prediction-Based adaptive variable ordering heuristics for constraint satisfaction problems
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– volume: vol. 5
  start-page: 81
  year: 2005
  end-page: 89
  ident: b20
  article-title: Randomized large neighborhood search for cumulative scheduling
  publication-title: ICAPS
– start-page: 149
  year: 2015
  end-page: 157
  ident: b19
  article-title: Simple and scalable time-table filtering for the cumulative constraint
  publication-title: Principles and practice of constraint programming
– volume: 64
  start-page: 278
  year: 1993
  end-page: 285
  ident: b59
  article-title: Benchmarks for basic scheduling problems
  publication-title: European Journal of Operational Research
– reference: .
– start-page: 1859
  year: 2022
  end-page: 1865
  ident: b32
  article-title: Best heuristic identification for constraint satisfaction
  publication-title: 31st international joint conference on artificial intelligence
– reference: (pp. 530–535).
– volume: 177
  year: 2025
  ident: b69
  article-title: A constraint programming-based lower bounding procedure for the job shop scheduling problem
  publication-title: Computers & Operations Research
– volume: vol. 7
  start-page: 131
  year: 2007
  end-page: 136
  ident: b36
  article-title: Nogood recording from restarts
  publication-title: IJCAI
– year: 2018
  ident: b58
  article-title: Reinforcement learning: An introduction
– start-page: 802
  year: 2009
  end-page: 816
  ident: b61
  article-title: Edge finding filtering algorithm for discrete cumulative resources in
  publication-title: Principles and practice of constraint programming - CP 2009
– volume: 4
  start-page: 53
  year: 2001
  end-page: 64
  ident: b11
  article-title: Solving open benchmark instances for the job-shop problem by parallel head–tail adjustments
  publication-title: Journal of Scheduling
– volume: vol. 16
  start-page: 146
  year: 2004
  ident: b9
  article-title: Boosting systematic search by weighting constraints
  publication-title: ECAI
– volume: 308
  start-page: 990
  year: 2023
  end-page: 1006
  ident: b8
  article-title: Deep learning-driven scheduling algorithm for a single machine problem minimizing the total tardiness
  publication-title: European Journal of Operational Research
– year: 2020
  ident: b12
  article-title: Combining reinforcement learning and constraint programming for combinatorial optimization
– start-page: 270
  year: 2007
  end-page: 283
  ident: b33
  article-title: On the importance of parameter tuning in text categorization
  publication-title: Perspectives of systems informatics
– start-page: 290
  year: 2015
  end-page: 296
  ident: b6
  article-title: Multi-armed bandits for adaptive constraint propagation
  publication-title: Proceedings of the 24th international joint conference on artificial intelligence
– volume: 33
  start-page: 42
  issue: 1
  year: 2005
  ident: 10.1016/j.cie.2025.111413_b2
  article-title: Branching rules revisited
  publication-title: Operations Research Letters
  doi: 10.1016/j.orl.2004.04.002
– ident: 10.1016/j.cie.2025.111413_b43
  doi: 10.1145/378239.379017
– volume: 119
  start-page: 557
  issue: 3
  year: 1999
  ident: 10.1016/j.cie.2025.111413_b10
  article-title: Constraint satisfaction problems: Algorithms and applications
  publication-title: European Journal of Operational Research
  doi: 10.1016/S0377-2217(98)00364-6
– year: 2023
  ident: 10.1016/j.cie.2025.111413_b27
– volume: 32
  issue: 1
  year: 2018
  ident: 10.1016/j.cie.2025.111413_b66
  article-title: Learning robust search strategies using a Bandit-Based approach
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
  doi: 10.1609/aaai.v32i1.12211
– volume: 34
  start-page: 391
  issue: 3
  year: 1988
  ident: 10.1016/j.cie.2025.111413_b3
  article-title: The shifting bottleneck procedure for job shop scheduling
  publication-title: Management Science
  doi: 10.1287/mnsc.34.3.391
– volume: 263
  year: 2023
  ident: 10.1016/j.cie.2025.111413_b53
  article-title: Multi-level lot-sizing and job shop scheduling with lot-streaming: Reformulation and solution approaches
  publication-title: International Journal of Production Economics
  doi: 10.1016/j.ijpe.2023.108958
– volume: vol. 16
  start-page: 146
  year: 2004
  ident: 10.1016/j.cie.2025.111413_b9
  article-title: Boosting systematic search by weighting constraints
– start-page: 71
  year: 2019
  ident: 10.1016/j.cie.2025.111413_b65
  article-title: Refining constraint weighting
– year: 2023
  ident: 10.1016/j.cie.2025.111413_b47
– year: 2012
  ident: 10.1016/j.cie.2025.111413_b49
– start-page: 228
  year: 2012
  ident: 10.1016/j.cie.2025.111413_b42
  article-title: Activity-based search for black-box constraint programming solvers
– start-page: 340
  year: 2025
  ident: 10.1016/j.cie.2025.111413_b45
  article-title: Bottleneck identification in Resource-Constrained project scheduling via constraint relaxation
– year: 1995
  ident: 10.1016/j.cie.2025.111413_b5
– volume: 177
  year: 2025
  ident: 10.1016/j.cie.2025.111413_b69
  article-title: A constraint programming-based lower bounding procedure for the job shop scheduling problem
  publication-title: Computers & Operations Research
  doi: 10.1016/j.cor.2024.106964
– volume: 109
  start-page: 137
  issue: 1
  year: 1998
  ident: 10.1016/j.cie.2025.111413_b16
  article-title: Benchmarks for shop scheduling problems
  publication-title: European Journal of Operational Research
  doi: 10.1016/S0377-2217(97)00019-2
– start-page: 392
  year: 2021
  ident: 10.1016/j.cie.2025.111413_b13
  article-title: SeaPearl: A constraint programming solver guided by reinforcement learning
– ident: 10.1016/j.cie.2025.111413_b22
– volume: 308
  start-page: 990
  issue: 3
  year: 2023
  ident: 10.1016/j.cie.2025.111413_b8
  article-title: Deep learning-driven scheduling algorithm for a single machine problem minimizing the total tardiness
  publication-title: European Journal of Operational Research
  doi: 10.1016/j.ejor.2022.11.034
– volume: 37
  start-page: 12444
  issue: 10
  year: 2023
  ident: 10.1016/j.cie.2025.111413_b30
  article-title: Large-State reinforcement learning for Hyper-Heuristics
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
  doi: 10.1609/aaai.v37i10.26466
– start-page: 290
  year: 2015
  ident: 10.1016/j.cie.2025.111413_b6
  article-title: Multi-armed bandits for adaptive constraint propagation
– volume: 38
  start-page: 1495
  issue: 10
  year: 1992
  ident: 10.1016/j.cie.2025.111413_b57
  article-title: New search spaces for sequencing problems with application to job shop scheduling
  publication-title: Management Science
  doi: 10.1287/mnsc.38.10.1495
– volume: 58
  start-page: 91
  issue: 1
  year: 2022
  ident: 10.1016/j.cie.2025.111413_b50
  article-title: An overview of machine learning techniques in constraint solving
  publication-title: Journal of Intelligent Information Systems
  doi: 10.1007/s10844-021-00666-5
– volume: 26
  start-page: 9
  issue: 2
  year: 2020
  ident: 10.1016/j.cie.2025.111413_b28
  article-title: Why tuning the control parameters of metaheuristic algorithms is so important for fair comparison?
  publication-title: Mendel
  doi: 10.13164/mendel.2020.2.009
– volume: 35
  start-page: 3931
  issue: 5
  year: 2021
  ident: 10.1016/j.cie.2025.111413_b70
  article-title: Parameterizing Branch-and-Bound search trees to learn branching policies
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
  doi: 10.1609/aaai.v35i5.16512
– start-page: 121
  year: 2008
  ident: 10.1016/j.cie.2025.111413_b41
  article-title: Multi-Armed Bandit problems
– volume: vol. 7
  start-page: 131
  year: 2007
  ident: 10.1016/j.cie.2025.111413_b36
  article-title: Nogood recording from restarts
– start-page: 123
  year: 2016
  ident: 10.1016/j.cie.2025.111413_b37
  article-title: Learning rate based branching heuristic for SAT solvers
– year: 2023
  ident: 10.1016/j.cie.2025.111413_b60
– ident: 10.1016/j.cie.2025.111413_b4
  doi: 10.1145/3292500.3330701
– volume: vol. 2
  start-page: 283
  year: 1992
  ident: 10.1016/j.cie.2025.111413_b68
  article-title: A genetic algorithm applicable to large-scale job-shop problems
– volume: 115
  year: 2023
  ident: 10.1016/j.cie.2025.111413_b18
  article-title: Scheduling of Multi-Robot job shop systems in dynamic environments: Mixed-Integer linear programming and constraint programming approaches
  publication-title: Omega
  doi: 10.1016/j.omega.2022.102770
– volume: 30
  issue: 1
  year: 2016
  ident: 10.1016/j.cie.2025.111413_b29
  article-title: Learning to branch in mixed integer programming
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
  doi: 10.1609/aaai.v30i1.10080
– year: 2022
  ident: 10.1016/j.cie.2025.111413_b17
  article-title: Online learning of variable ordering heuristics for constraint optimisation problems
  publication-title: Annals of Mathematics and Artificial Intelligence
– volume: vol. 5
  start-page: 81
  year: 2005
  ident: 10.1016/j.cie.2025.111413_b20
  article-title: Randomized large neighborhood search for cumulative scheduling
– volume: 96
  start-page: 205
  issue: 1
  year: 1997
  ident: 10.1016/j.cie.2025.111413_b31
  article-title: PSPLIB - a project scheduling problem library: OR software - orsep operations research software exchange program
  publication-title: European Journal of Operational Research
  doi: 10.1016/S0377-2217(96)00170-1
– volume: 64
  start-page: 278
  issue: 2
  year: 1993
  ident: 10.1016/j.cie.2025.111413_b59
  article-title: Benchmarks for basic scheduling problems
  publication-title: European Journal of Operational Research
  doi: 10.1016/0377-2217(93)90182-M
– year: 2012
  ident: 10.1016/j.cie.2025.111413_b62
– volume: 24
  start-page: 67
  issue: 1
  year: 2000
  ident: 10.1016/j.cie.2025.111413_b21
  article-title: Heavy-tailed phenomena in satisfiability and constraint satisfaction problems
  publication-title: Journal of Automated Reasoning
  doi: 10.1023/A:1006314320276
– start-page: 557
  year: 2004
  ident: 10.1016/j.cie.2025.111413_b51
  article-title: Impact-based search strategies for constraint programming
– year: 2023
  ident: 10.1016/j.cie.2025.111413_b44
  article-title: Mixed-Integer programming versus constraint programming for shop scheduling problems: New results and outlook
  publication-title: INFORMS Journal on Computing
  doi: 10.1287/ijoc.2023.1287
– volume: vol. 24
  start-page: 2249
  year: 2011
  ident: 10.1016/j.cie.2025.111413_b14
  article-title: An empirical evaluation of Thompson sampling
– volume: 58
  start-page: 527
  issue: 5
  year: 1952
  ident: 10.1016/j.cie.2025.111413_b52
  article-title: Some aspects of the sequential design of experiments
  publication-title: Bulletin of the American Mathematical Society
  doi: 10.1090/S0002-9904-1952-09620-8
– volume: 121
  year: 2020
  ident: 10.1016/j.cie.2025.111413_b15
  article-title: Going to the core of hard resource-constrained project scheduling instances
  publication-title: Computers & Operations Research
  doi: 10.1016/j.cor.2020.104976
– start-page: 437
  year: 2015
  ident: 10.1016/j.cie.2025.111413_b63
  article-title: Failure-directed search for constraint-based scheduling
– volume: 4
  start-page: 53
  issue: 1
  year: 2001
  ident: 10.1016/j.cie.2025.111413_b11
  article-title: Solving open benchmark instances for the job-shop problem by parallel head–tail adjustments
  publication-title: Journal of Scheduling
  doi: 10.1002/1099-1425(200101/02)4:1<53::AID-JOS59>3.0.CO;2-Y
– year: 2023
  ident: 10.1016/j.cie.2025.111413_b26
– year: 2023
  ident: 10.1016/j.cie.2025.111413_b46
– start-page: 464
  year: 2013
  ident: 10.1016/j.cie.2025.111413_b39
  article-title: Bandit-based search for constraint programming
– volume: 157
  year: 2008
  ident: 10.1016/j.cie.2025.111413_b38
  article-title: A constraint programming approach for the resource-constrained project scheduling problem
  publication-title: Annals of Operations Research
– start-page: 562
  year: 2013
  ident: 10.1016/j.cie.2025.111413_b48
  article-title: Time-table extended-edge-finding for the cumulative constraint
– start-page: 802
  year: 2009
  ident: 10.1016/j.cie.2025.111413_b61
  article-title: Edge finding filtering algorithm for discrete cumulative resources in O(knlogn)
– volume: 168
  year: 2022
  ident: 10.1016/j.cie.2025.111413_b1
  article-title: A new hybridization of adaptive large neighborhood search with constraint programming for open shop scheduling with sequence-dependent setup times
  publication-title: Computers & Industrial Engineering
  doi: 10.1016/j.cie.2022.108128
– volume: 39
  start-page: 11390
  issue: 11
  year: 2025
  ident: 10.1016/j.cie.2025.111413_b67
  article-title: Prediction-Based adaptive variable ordering heuristics for constraint satisfaction problems
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
  doi: 10.1609/aaai.v39i11.33239
– start-page: 149
  year: 2015
  ident: 10.1016/j.cie.2025.111413_b19
  article-title: Simple and scalable time-table filtering for the cumulative constraint
– year: 2023
  ident: 10.1016/j.cie.2025.111413_b54
– volume: 150
  year: 2020
  ident: 10.1016/j.cie.2025.111413_b23
  article-title: Resource-constrained multi-project scheduling with activity and time flexibility
  publication-title: Computers & Industrial Engineering
  doi: 10.1016/j.cie.2020.106857
– start-page: 74
  year: 2015
  ident: 10.1016/j.cie.2025.111413_b7
  article-title: Embedding decision trees and random forests in constraint programming
– volume: 39
  start-page: 3331
  issue: 12
  year: 2012
  ident: 10.1016/j.cie.2025.111413_b24
  article-title: A constraint programming based column generation approach to nurse rostering problems
  publication-title: Computers & Operations Research
  doi: 10.1016/j.cor.2012.04.018
– volume: 123
  year: 2020
  ident: 10.1016/j.cie.2025.111413_b40
  article-title: Mixed integer linear programming and constraint programming models for the online printing shop scheduling problem
  publication-title: Computers & Operations Research
  doi: 10.1016/j.cor.2020.105020
– start-page: 1859
  year: 2022
  ident: 10.1016/j.cie.2025.111413_b32
  article-title: Best heuristic identification for constraint satisfaction
– volume: vol. 325
  start-page: 479
  year: 2020
  ident: 10.1016/j.cie.2025.111413_b64
  article-title: Learning variable ordering heuristics with Multi-Armed bandits and restarts
– start-page: 417
  year: 1998
  ident: 10.1016/j.cie.2025.111413_b56
  article-title: Using constraint programming and local search methods to solve vehicle routing problems
– year: 2020
  ident: 10.1016/j.cie.2025.111413_b12
– year: 2025
  ident: 10.1016/j.cie.2025.111413_b55
– volume: 173
  start-page: 1592
  issue: 18
  year: 2009
  ident: 10.1016/j.cie.2025.111413_b35
  article-title: Reasoning from last conflict(s) in constraint programming
  publication-title: Artificial Intelligence
  doi: 10.1016/j.artint.2009.09.002
– start-page: 270
  year: 2007
  ident: 10.1016/j.cie.2025.111413_b33
  article-title: On the importance of parameter tuning in text categorization
– year: 2018
  ident: 10.1016/j.cie.2025.111413_b58
– year: 2014
  ident: 10.1016/j.cie.2025.111413_b34
– volume: 172
  year: 2022
  ident: 10.1016/j.cie.2025.111413_b25
  article-title: Constraint programming and constructive heuristics for parallel machine scheduling with sequence-dependent setups and common servers
  publication-title: Computers & Industrial Engineering
  doi: 10.1016/j.cie.2022.108586
SSID ssj0004591
Score 2.4592643
Snippet Failure-Directed Search (FDS) is a significant complete generic search algorithm used in Constraint Programming (CP) to efficiently explore the search space,...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 111413
SubjectTerms Constraint Programming
Discrete optimization
Heuristics
Reinforcement learning
Scheduling
Tree search
Title Reinforcement learning for search tree size minimization in Constraint Programming: New results on scheduling benchmarks
URI https://dx.doi.org/10.1016/j.cie.2025.111413
Volume 209
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: ScienceDirect database
  issn: 0360-8352
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0004591
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELaWlgMcKBQQpYB84ESVVeokdsytpUWAUIVQqVZcoqxjq2k3odpsqxX_hf_K-FW7hUr0gLSKVk7izWY-fZ4ZzwOh1wRWbarqJqGC5UkuGpVMac6TNCONFJyRxvghjz6zg4NyMuFfRqNfPhfmYsb6vlwu-dl_FTWMgbB16uwtxH05KQzAdxA6HEHscPwnwX-VphiqMH4_3xXCRks6F4feiN4a2p9ySxcW6Vwmpsv_G0zTiIXOINCBW51LiNZxkGCZn8_s_gLYxLBGmVT2Kfz5466enw6xouu7RQwGW21oECJDAcTgh21748c-amd2477zp_zIXueCieeBMuEefWp7Jg2jf9cMCqox3z2NXRmkcDl9gfEymiZaJYzpmaQ8Ilig5twmr_7B_dYNcTIGThzr2cfh2qt1tq-tf5dRiT7g7aSCKSo9RWWnuINWCSs4kObqzsf9yaeoHL1tyeif22-bmwDCa8_xd8UnUmYOH6IHzgrBOxY9j9BI9utozVkk2PH9sI7uR-UqH6PlFWhhDy0MQ9hCC2toYQ0tHEMLtz0O0MIRtN5iABZ2wMJwZQAWDsB6gr693z989yFxnTsSAeLKEm318iwrVE62U0GLqS5Lp7gAY1YoykTdqEKVGaj7sqhLWZeNoKUg8OFZwQTLnqKV_kcvnyGcpkoWDWG1KmVOdQUETSGgeMErFYLyDfTGv9bqzBZoqW4U5AbK_YuvnIZpNccKQHTzbc9v8xub6F7A9gu0spify5forrhYtMP8lUPQbzrxnB8
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=Reinforcement+learning+for+search+tree+size+minimization+in+Constraint+Programming%3A+New+results+on+scheduling+benchmarks&rft.jtitle=Computers+%26+industrial+engineering&rft.au=Heinz%2C+Vil%C3%A9m&rft.au=Vil%C3%ADm%2C+Petr&rft.au=Hanz%C3%A1lek%2C+Zden%C4%9Bk&rft.date=2025-11-01&rft.issn=0360-8352&rft.volume=209&rft.spage=111413&rft_id=info:doi/10.1016%2Fj.cie.2025.111413&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_cie_2025_111413
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0360-8352&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0360-8352&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0360-8352&client=summon