A Scalable Reinforcement Learning Algorithm for Scheduling Railway Lines

This paper describes an algorithm for scheduling bidirectional railway lines (both single- and multi-track) using a reinforcement learning (RL) approach. The goal is to define the track allocations and arrival/departure times for all trains on the line, given their initial positions, priority, halt...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on intelligent transportation systems Vol. 20; no. 2; pp. 727 - 736
Main Author: Khadilkar, Harshad
Format: Journal Article
Language:English
Published: New York IEEE 01.02.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
ISSN:1524-9050, 1558-0016
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract This paper describes an algorithm for scheduling bidirectional railway lines (both single- and multi-track) using a reinforcement learning (RL) approach. The goal is to define the track allocations and arrival/departure times for all trains on the line, given their initial positions, priority, halt times, and traversal times, while minimizing the total priority-weighted delay. The primary advantage of the proposed algorithm compared to exact approaches is its scalability, and compared to heuristic approaches is its solution quality. Efficient scaling is ensured by decoupling the size of the state-action space from the size of the problem instance. Improved solution quality is obtained because of the inherent adaptability of reinforcement learning to specific problem instances. An additional advantage is that the learning from one instance can be transferred with minimal re-learning to another instance with different infrastructure resources and traffic mix. It is shown that the solution quality of the RL algorithm exceeds that of two prior heuristic-based approaches while having comparable computation times. Two lines from the Indian rail network are used for demonstrating the applicability of the proposed algorithm in the real world.
AbstractList This paper describes an algorithm for scheduling bidirectional railway lines (both single- and multi-track) using a reinforcement learning (RL) approach. The goal is to define the track allocations and arrival/departure times for all trains on the line, given their initial positions, priority, halt times, and traversal times, while minimizing the total priority-weighted delay. The primary advantage of the proposed algorithm compared to exact approaches is its scalability, and compared to heuristic approaches is its solution quality. Efficient scaling is ensured by decoupling the size of the state-action space from the size of the problem instance. Improved solution quality is obtained because of the inherent adaptability of reinforcement learning to specific problem instances. An additional advantage is that the learning from one instance can be transferred with minimal re-learning to another instance with different infrastructure resources and traffic mix. It is shown that the solution quality of the RL algorithm exceeds that of two prior heuristic-based approaches while having comparable computation times. Two lines from the Indian rail network are used for demonstrating the applicability of the proposed algorithm in the real world.
Author Khadilkar, Harshad
Author_xml – sequence: 1
  givenname: Harshad
  orcidid: 0000-0003-3601-778X
  surname: Khadilkar
  fullname: Khadilkar, Harshad
  email: harshad.khadilkar@tcs.com
  organization: TCS Research, Tata Consultancy Services, Mumbai, India
BookMark eNp9kEFrwkAQhZdioWr7A0ovgZ5jd3azSfYo0lZBKKg9L5vdia7Ejd1Eiv--CUoPPfQ0w8z75jFvRAa-9kjII9AJAJUvm8VmPWEU8gnLmYRU3JAhCJHHlEI66HuWxJIKekdGTbPvpokAGJL5NFobXemiwmiFzpd1MHhA30ZL1ME7v42m1bYOrt0dom7ZqXdoT1W_WGlXfetztHQem3tyW-qqwYdrHZPPt9fNbB4vP94Xs-kyNkzyNhbUFLagAEmGmWClTahOmYDSZDwvNEcLXOYFUmZ4ai0IK60tOU8oLUsjCj4mz5e7x1B_nbBp1b4-Bd9ZKgaZ4HlGhexUcFGZUDdNwFIdgzvocFZAVR-Y6gNTfWDqGljHZH8Y41rdutq3ofv0X_LpQjpE_HXKucgklfwHqmB6Wg
CODEN ITISFG
CitedBy_id crossref_primary_10_1007_s10479_021_04178_x
crossref_primary_10_1016_j_jrtpm_2024_100483
crossref_primary_10_1177_03611981241302335
crossref_primary_10_1016_j_ifacol_2023_10_1503
crossref_primary_10_1016_j_ifacol_2024_07_358
crossref_primary_10_1515_comp_2024_0014
crossref_primary_10_1109_TITS_2021_3131202
crossref_primary_10_1109_JIOT_2022_3152381
crossref_primary_10_1109_TNNLS_2024_3357494
crossref_primary_10_1007_s11227_025_07399_0
crossref_primary_10_1016_j_tre_2024_103900
crossref_primary_10_1016_j_swevo_2024_101517
crossref_primary_10_1109_MITS_2020_2970180
crossref_primary_10_1007_s00521_021_06129_w
crossref_primary_10_1109_TITS_2025_3547473
crossref_primary_10_1016_j_cie_2025_111329
crossref_primary_10_3390_app10238367
crossref_primary_10_1080_21680566_2023_2179461
crossref_primary_10_1016_j_jrtpm_2023_100394
crossref_primary_10_1109_TCYB_2023_3312647
crossref_primary_10_1109_TETC_2020_3030984
crossref_primary_10_1177_03611981251339168
crossref_primary_10_1109_TIV_2023_3305536
crossref_primary_10_1109_TITS_2023_3344468
crossref_primary_10_3390_en14164776
crossref_primary_10_3390_app13179547
crossref_primary_10_1016_j_tre_2020_102176
crossref_primary_10_1007_s13177_025_00500_0
crossref_primary_10_1016_j_ress_2023_109136
crossref_primary_10_1109_JAS_2023_123501
crossref_primary_10_3390_rs13122377
crossref_primary_10_1109_TITS_2023_3319135
crossref_primary_10_1016_j_trc_2022_103679
crossref_primary_10_1109_TNNLS_2023_3309689
crossref_primary_10_1177_0361198120917388
crossref_primary_10_1111_exsy_13315
crossref_primary_10_1109_TITS_2023_3305074
crossref_primary_10_1016_j_jmsy_2022_11_010
crossref_primary_10_3390_app14198642
crossref_primary_10_1016_j_jrtpm_2023_100427
crossref_primary_10_1016_j_trb_2023_02_015
crossref_primary_10_1061_JMENEA_MEENG_4883
crossref_primary_10_1016_j_trc_2025_105215
crossref_primary_10_1016_j_trpro_2021_07_119
crossref_primary_10_1038_s41598_023_29526_8
crossref_primary_10_1007_s12652_020_02862_7
crossref_primary_10_1109_TITS_2022_3229527
crossref_primary_10_3390_rs16234436
crossref_primary_10_1109_TITS_2021_3131637
crossref_primary_10_1016_j_tre_2022_102712
crossref_primary_10_1016_j_asoc_2023_110590
crossref_primary_10_1016_j_eswa_2021_114663
crossref_primary_10_1093_tse_tdad007
crossref_primary_10_1109_TCSS_2021_3119944
crossref_primary_10_1007_s10845_021_01847_3
crossref_primary_10_1016_j_trc_2023_104155
crossref_primary_10_1016_j_trc_2024_104970
crossref_primary_10_1016_j_trc_2024_104976
crossref_primary_10_1109_TASE_2023_3338695
crossref_primary_10_1016_j_trc_2023_104237
crossref_primary_10_1080_00207543_2025_2481184
crossref_primary_10_1109_TSMC_2023_3346401
crossref_primary_10_3390_rs17121972
crossref_primary_10_3390_app14041552
Cites_doi 10.1287/opre.14.5.801
10.1016/j.cor.2008.12.012
10.1016/j.trb.2015.03.004
10.1109/TITS.2012.2234118
10.1016/S0377-2217(77)81007-2
10.1016/j.trb.2013.10.013
10.1016/0305-0548(94)90099-X
10.1109/TITS.2014.2320757
10.1109/TITS.2014.2379617
10.1023/A:1021255214371
10.1016/j.jrtpm.2014.04.001
10.1016/S0022-0000(75)80008-0
10.1016/S0377-2217(97)00317-2
10.1080/07408179808966488
10.1177/0954409714565654
10.1049/pe:19950408
10.1016/j.trc.2012.11.001
10.1016/j.trb.2016.01.004
10.1016/0191-2615(95)00022-4
10.1016/j.jrtpm.2016.06.004
10.23919/ACC.2017.7963829
10.1109/TITS.2015.2446985
10.1016/j.neunet.2014.09.003
10.1023/A:1009672832658
10.1016/j.ejor.2006.10.034
10.1287/trsc.8.1.65
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
FR3
JQ2
KR7
L7M
L~C
L~D
DOI 10.1109/TITS.2018.2829165
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
Engineering Research Database
ProQuest Computer Science Collection
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Civil Engineering Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Civil Engineering Abstracts

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-0016
EndPage 736
ExternalDocumentID 10_1109_TITS_2018_2829165
8357909
Genre orig-research
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AIBXA
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
HZ~
H~9
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
ZY4
AAYXX
CITATION
7SC
7SP
8FD
FR3
JQ2
KR7
L7M
L~C
L~D
ID FETCH-LOGICAL-c293t-50cbdb01147e752fd40a6251fc738ba3ed1398be02c36dd15d9ddf33400ffc5b3
IEDL.DBID RIE
ISICitedReferencesCount 88
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000460756900027&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1524-9050
IngestDate Sun Nov 30 04:27:10 EST 2025
Sat Nov 29 06:34:52 EST 2025
Tue Nov 18 21:52:55 EST 2025
Wed Aug 27 03:06:24 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c293t-50cbdb01147e752fd40a6251fc738ba3ed1398be02c36dd15d9ddf33400ffc5b3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-3601-778X
PQID 2175387059
PQPubID 75735
PageCount 10
ParticipantIDs crossref_primary_10_1109_TITS_2018_2829165
proquest_journals_2175387059
crossref_citationtrail_10_1109_TITS_2018_2829165
ieee_primary_8357909
PublicationCentury 2000
PublicationDate 2019-02-01
PublicationDateYYYYMMDD 2019-02-01
PublicationDate_xml – month: 02
  year: 2019
  text: 2019-02-01
  day: 01
PublicationDecade 2010
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on intelligent transportation systems
PublicationTitleAbbrev TITS
PublicationYear 2019
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref35
ref13
ref34
ref12
ref15
ref14
randløv (ref33) 1998
ref11
ref10
sutton (ref7) 2012
ref2
ref1
hirashima (ref25) 2011; 38
ref16
ref19
ref18
(ref36) 2013
zhang (ref28) 1996; 8
ref23
ref26
ref20
hirashima (ref24) 2010
ref22
ref21
grzybowski (ref30) 2011; 19
hill (ref8) 1995; 9
shalev-shwartz (ref32) 2016
ref29
(ref37) 2015
ref9
ref4
zhang (ref27) 1995
ref3
ref6
cai (ref17) 1998; 30
ref5
boyan (ref31) 1992
References_xml – start-page: 1
  year: 2010
  ident: ref24
  article-title: A reinforcement learning system for transfer scheduling of freight cars in a train
  publication-title: Proc Int Multiconf Eng Comput Sci
– ident: ref14
  doi: 10.1287/opre.14.5.801
– start-page: 1
  year: 1995
  ident: ref27
  article-title: A reinforcement learning approach to job-shop scheduling
  publication-title: Proc Int Joint Conf Artif Intell
– ident: ref3
  doi: 10.1016/j.cor.2008.12.012
– ident: ref16
  doi: 10.1016/j.trb.2015.03.004
– ident: ref22
  doi: 10.1109/TITS.2012.2234118
– volume: 19
  start-page: 147
  year: 2011
  ident: ref30
  article-title: Monte Carlo analysis of risk measures for blackjack type optimal stopping problems
  publication-title: Eng Lett
– ident: ref34
  doi: 10.1016/S0377-2217(77)81007-2
– ident: ref15
  doi: 10.1016/j.trb.2013.10.013
– ident: ref4
  doi: 10.1016/0305-0548(94)90099-X
– ident: ref23
  doi: 10.1109/TITS.2014.2320757
– ident: ref11
  doi: 10.1109/TITS.2014.2379617
– ident: ref18
  doi: 10.1023/A:1021255214371
– year: 2016
  ident: ref32
  publication-title: Safe Multi-Agent Reinforcement Learning for Autonomous Driving
– ident: ref9
  doi: 10.1016/j.jrtpm.2014.04.001
– ident: ref1
  doi: 10.1016/S0022-0000(75)80008-0
– volume: 8
  start-page: 1024
  year: 1996
  ident: ref28
  article-title: High-performance job-shop scheduling with a time-delay TD( $\lambda $ ) network
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref35
  doi: 10.1016/S0377-2217(97)00317-2
– year: 2015
  ident: ref37
  publication-title: Train timetable and operational data archives
– year: 2012
  ident: ref7
  publication-title: Reinforcement Learning An Introduction
– volume: 30
  start-page: 481
  year: 1998
  ident: ref17
  article-title: Greedy heuristics for rapid scheduling of trains on a single track
  publication-title: IIE Trans
  doi: 10.1080/07408179808966488
– ident: ref26
  doi: 10.1177/0954409714565654
– volume: 9
  start-page: 201
  year: 1995
  ident: ref8
  article-title: electric railway traction. iv. signalling and interlockings
  publication-title: Power Engineering Journal
  doi: 10.1049/pe:19950408
– ident: ref21
  doi: 10.1016/j.trc.2012.11.001
– ident: ref29
  doi: 10.1016/j.trb.2016.01.004
– year: 1992
  ident: ref31
  article-title: Modular neural networks for learning context-dependent game strategies
– volume: 38
  start-page: 242
  year: 2011
  ident: ref25
  article-title: A reinforcement learning method for train marshaling based on movements of locomotive
  publication-title: IAENG Int J Comput Sci
– year: 2013
  ident: ref36
  publication-title: R A Language and Environment for Statistical Computing
– ident: ref5
  doi: 10.1016/0191-2615(95)00022-4
– ident: ref19
  doi: 10.1016/j.jrtpm.2016.06.004
– ident: ref20
  doi: 10.23919/ACC.2017.7963829
– start-page: 463
  year: 1998
  ident: ref33
  article-title: Learning to drive a bicycle using reinforcement learning and shaping
  publication-title: Proc Int Conf Mach Learn
– ident: ref10
  doi: 10.1109/TITS.2015.2446985
– ident: ref12
  doi: 10.1016/j.neunet.2014.09.003
– ident: ref6
  doi: 10.1023/A:1009672832658
– ident: ref2
  doi: 10.1016/j.ejor.2006.10.034
– ident: ref13
  doi: 10.1287/trsc.8.1.65
SSID ssj0014511
Score 2.5585291
Snippet This paper describes an algorithm for scheduling bidirectional railway lines (both single- and multi-track) using a reinforcement learning (RL) approach. The...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 727
SubjectTerms Algorithms
Allocations
Decoupling
Delays
Heuristic methods
Learning (artificial intelligence)
Machine learning
Processor scheduling
Production scheduling
Rail transportation
Schedules
Scheduling
Tracking
Trains
Title A Scalable Reinforcement Learning Algorithm for Scheduling Railway Lines
URI https://ieeexplore.ieee.org/document/8357909
https://www.proquest.com/docview/2175387059
Volume 20
WOSCitedRecordID wos000460756900027&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-0016
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014511
  issn: 1524-9050
  databaseCode: RIE
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF5q8aAHX1WsVtmDJzHt5rHZ7LGIpUIp0lbpLST7qIXaSpsq_nt3NmkoKIKXEMhMCDPZnfe3CN3IKAwkp8rh5uoEjCYO11o7iUtSPwqkp2xO96XH-v1oPOZPFXRXzsIopWzzmWrCra3ly4VYQ6qsZbwFxmFab4exMJ_VKisGgLNlsVG9wOGEbiqYLuGt0eNoCE1cURPKhi7YkS0bZA9V-bETW_PSOfzfhx2hg8KNxO1c78eoouYnaH8LXLCGum08NAqA0Sg8UBYgVdhcIC4wVSe4PZssltPs9Q2bh4b61dgdGE_Hg2Q6-0y-cA-a4k_Rc-dhdN91inMTHGGMd-ZQIlKZQqTDFKOelgFJTJjjasH8KE18JY3bF6WKeMIPpXSp5FJq3zfLWWtBU_8MVeeLuTpH2DMOGSPaE6FSQSjSJBCGz3h5GhBto7SOyEaSsShAxeFsi1lsgwvCYxB-DMKPC-HX0W3J8p4javxFXANpl4SFoOuosVFXXKy5VewB6KjZfii_-J3rEu2Zd_O857qBqtlyra7QrvjIpqvltf2dvgHYncdq
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5EBfXgW6xW3YMnMe0m2W2yxyJKi7WIVvEWkn20hdpKmyr-e3e2aREUwUsIZIaEmezO-1uAcxXXmBJce8JePRbx1BPGGC_1aRbGTAXa5XSfW1G7Hb-8iPsluFzMwmitXfOZruCtq-WrkZxiqqxqvYVI4LTeCmcsoLNprUXNAJG2HDpqwDxB-byG6VNR7TQ7j9jGFVewcOijJflmhdyxKj_2Ymdgbrb-92nbsFk4kqQ-0_wOLOnhLmx8gxfcg0adPFoV4HAUedAOIlW6bCApUFW7pD7ojsb9vPdK7ENL3bOWBwfUyUPaH3ykn6SFbfH78HRz3blqeMXJCZ605jv3OJWZyjDWiXTEA6MYTW2g4xsZhXGWhlpZxy_ONA1kWFPK50ooZcLQLmhjJM_CA1gejob6EEhgXbKImkDWtGY1maVMWj7r5xnEtI2zEtC5JBNZwIrj6RaDxIUXVCQo_ASFnxTCL8HFguVthqnxF_EeSntBWAi6BOW5upJi1U2SAGFH7QbExdHvXGew1ujctZJWs317DOv2PWLWgV2G5Xw81SewKt_z_mR86n6tL2NbyrE
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=A+Scalable+Reinforcement+Learning+Algorithm+for+Scheduling+Railway+Lines&rft.jtitle=IEEE+transactions+on+intelligent+transportation+systems&rft.au=Khadilkar%2C+Harshad&rft.date=2019-02-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1524-9050&rft.eissn=1558-0016&rft.volume=20&rft.issue=2&rft.spage=727&rft_id=info:doi/10.1109%2FTITS.2018.2829165&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1524-9050&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1524-9050&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1524-9050&client=summon