Simulation optimization of highway hard shoulder running based on multi-agent deep deterministic policy gradient algorithm

To alleviate traffic congestion and reduce vehicle emissions, the use of hard shoulder running (HSR) has emerged as a sustainable and cost-effective active traffic management technology. However, optimizing the utilization of HSR remains a critical challenge for improving highway traffic congestion....

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Alexandria engineering journal Ročník 117; s. 99 - 115
Hlavní autori: Hu, Lipeng, Tang, Jinjun, Zou, Guoqing, Li, Zhitao, Zeng, Jie, Li, Mingyang
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 01.04.2025
Elsevier
Predmet:
ISSN:1110-0168
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract To alleviate traffic congestion and reduce vehicle emissions, the use of hard shoulder running (HSR) has emerged as a sustainable and cost-effective active traffic management technology. However, optimizing the utilization of HSR remains a critical challenge for improving highway traffic congestion. To tackle this issue, the Multi-Agent Deep Deterministic Policy Gradient with spatio-temporal constraints (STC-MADDPG) algorithm based on multi-agent reinforcement learning is proposed in this paper. To verify the effectiveness of the proposed algorithm, the present study utilizes a Simulation of Urban Mobility (SUMO) platform to construct a simulation environment. The optimal HSR strategy is then determined for four different service levels of highways. Additionally, the granularity of control is adjusted by varying the number of agents, allowing for a comprehensive analysis and evaluation of the varying effectiveness of different control levels across different service levels. Through in-depth investigation into the two strategies under the fourth service level, it is discovered that fewer sections each agent controls yields better results when congestion becomes more severe. The experimental results clearly demonstrate the superiority of the optimized strategy for HSR using the STC-MADDPG algorithm, compared to the “no open” strategy. Specifically, the maximum reductions achieved in terms of total vehicle travel time, Time Integrated Time-to-collision, CO emissions, CO2 emissions, and NOx emissions are 37.4 %, 34.1 %, 28.0 %, 17.1 %, and 27.2 % respectively. This comprehensive evaluation of the algorithm's effectiveness covers three key aspects: driving efficiency, driving safety, and environmental protection. The findings conclusively demonstrate the positive impact of the proposed algorithm on all three fronts. •We propose a spatio-temporal MARL algorithm to optimize HSR strategy.•The method’s effectiveness in efficiency, emissions, and safety across four levels is assessed using the SUMO.•An extended study compares strategies with 4 and 8 agents at service level 4 under severe congestion.•The results of the evaluation confirmed the validity of the proposed methodology through actual case testing.
AbstractList To alleviate traffic congestion and reduce vehicle emissions, the use of hard shoulder running (HSR) has emerged as a sustainable and cost-effective active traffic management technology. However, optimizing the utilization of HSR remains a critical challenge for improving highway traffic congestion. To tackle this issue, the Multi-Agent Deep Deterministic Policy Gradient with spatio-temporal constraints (STC-MADDPG) algorithm based on multi-agent reinforcement learning is proposed in this paper. To verify the effectiveness of the proposed algorithm, the present study utilizes a Simulation of Urban Mobility (SUMO) platform to construct a simulation environment. The optimal HSR strategy is then determined for four different service levels of highways. Additionally, the granularity of control is adjusted by varying the number of agents, allowing for a comprehensive analysis and evaluation of the varying effectiveness of different control levels across different service levels. Through in-depth investigation into the two strategies under the fourth service level, it is discovered that fewer sections each agent controls yields better results when congestion becomes more severe. The experimental results clearly demonstrate the superiority of the optimized strategy for HSR using the STC-MADDPG algorithm, compared to the “no open” strategy. Specifically, the maximum reductions achieved in terms of total vehicle travel time, Time Integrated Time-to-collision, CO emissions, CO2 emissions, and NOx emissions are 37.4 %, 34.1 %, 28.0 %, 17.1 %, and 27.2 % respectively. This comprehensive evaluation of the algorithm's effectiveness covers three key aspects: driving efficiency, driving safety, and environmental protection. The findings conclusively demonstrate the positive impact of the proposed algorithm on all three fronts. •We propose a spatio-temporal MARL algorithm to optimize HSR strategy.•The method’s effectiveness in efficiency, emissions, and safety across four levels is assessed using the SUMO.•An extended study compares strategies with 4 and 8 agents at service level 4 under severe congestion.•The results of the evaluation confirmed the validity of the proposed methodology through actual case testing.
To alleviate traffic congestion and reduce vehicle emissions, the use of hard shoulder running (HSR) has emerged as a sustainable and cost-effective active traffic management technology. However, optimizing the utilization of HSR remains a critical challenge for improving highway traffic congestion. To tackle this issue, the Multi-Agent Deep Deterministic Policy Gradient with spatio-temporal constraints (STC-MADDPG) algorithm based on multi-agent reinforcement learning is proposed in this paper. To verify the effectiveness of the proposed algorithm, the present study utilizes a Simulation of Urban Mobility (SUMO) platform to construct a simulation environment. The optimal HSR strategy is then determined for four different service levels of highways. Additionally, the granularity of control is adjusted by varying the number of agents, allowing for a comprehensive analysis and evaluation of the varying effectiveness of different control levels across different service levels. Through in-depth investigation into the two strategies under the fourth service level, it is discovered that fewer sections each agent controls yields better results when congestion becomes more severe. The experimental results clearly demonstrate the superiority of the optimized strategy for HSR using the STC-MADDPG algorithm, compared to the “no open” strategy. Specifically, the maximum reductions achieved in terms of total vehicle travel time, Time Integrated Time-to-collision, CO emissions, CO2 emissions, and NOx emissions are 37.4 %, 34.1 %, 28.0 %, 17.1 %, and 27.2 % respectively. This comprehensive evaluation of the algorithm's effectiveness covers three key aspects: driving efficiency, driving safety, and environmental protection. The findings conclusively demonstrate the positive impact of the proposed algorithm on all three fronts.
Author Tang, Jinjun
Li, Zhitao
Hu, Lipeng
Zeng, Jie
Li, Mingyang
Zou, Guoqing
Author_xml – sequence: 1
  givenname: Lipeng
  surname: Hu
  fullname: Hu, Lipeng
  organization: Smart Transport Key Laboratory of Hunan Province, School of Traffic and Transportation Engineering, Central South University, Changsha, China
– sequence: 2
  givenname: Jinjun
  surname: Tang
  fullname: Tang, Jinjun
  email: jinjuntang@csu.edu.cn
  organization: Smart Transport Key Laboratory of Hunan Province, School of Traffic and Transportation Engineering, Central South University, Changsha, China
– sequence: 3
  givenname: Guoqing
  surname: Zou
  fullname: Zou, Guoqing
  organization: Hunan Pingyi Expressway Construction Development Company Limited, Yueyang, China
– sequence: 4
  givenname: Zhitao
  surname: Li
  fullname: Li, Zhitao
  organization: Smart Transport Key Laboratory of Hunan Province, School of Traffic and Transportation Engineering, Central South University, Changsha, China
– sequence: 5
  givenname: Jie
  surname: Zeng
  fullname: Zeng, Jie
  organization: Smart Transport Key Laboratory of Hunan Province, School of Traffic and Transportation Engineering, Central South University, Changsha, China
– sequence: 6
  givenname: Mingyang
  surname: Li
  fullname: Li, Mingyang
  organization: Smart Transport Key Laboratory of Hunan Province, School of Traffic and Transportation Engineering, Central South University, Changsha, China
BookMark eNp9kT1u3DAQhVk4QGzHB0jHC0jhjyRKSBUYTmLAgIskNTErDqURJHFBcW2sTx-u12lSmAUHQ8738PDmil2sYUXGPktRSiGbL1MJOJVKqKqUqpRSXLBLmUuRP9uP7GbbJpFPbbqqay7Zyy9aDjMkCisP-0QLvbw1no80jM9w5CNEx7cxHGaHkcfDutI68B1s6HiezHyiAgZcE3eI-3wljAuttCXq-T7M1B_5EMHRaQTmIURK4_KJffAwb3jzVq_Zn-93v29_Fg-PP-5vvz0UfSWaVFRGt9ipbieUU43QqnWqh1o7J1swnd9p3Xa188ob07UaK6gqD0YZj6KWHvU1uz_rugCT3UdaIB5tALKvDyEOFmJ2OqOVWAutTau6uskqGhpZYd35RlVt7VqTtcxZq49h2yJ621N6DSxFoNlKYU9bsJPNW7CnLVipbI4_k_I_8p-T95ivZwZzPE-E0W59zrBHRxH7lP3TO_Rf8CSlOA
CitedBy_id crossref_primary_10_1016_j_asej_2025_103750
Cites_doi 10.3141/2111-02
10.1007/978-3-030-60990-0_12
10.17226/26394
10.2352/ISSN.2470-1173.2017.19.AVM-023
10.1109/TCYB.2020.2977374
10.1016/j.autcon.2024.105302
10.1016/j.simpat.2017.03.003
10.1109/ICCEAI55464.2022.00029
10.1016/j.simpat.2014.06.005
10.3390/su15043479
10.3141/2279-12
10.1177/0361198119900502
10.1016/j.trc.2010.12.006
10.1038/nature14236
10.1049/iet-its.2016.0345
10.1016/j.aej.2022.02.042
10.1016/j.aej.2022.12.057
10.1109/TITS.2019.2942050
10.3390/app9173614
10.1109/ITSC.2010.5625159
10.3141/2280-02
10.1038/nature14539
10.3390/su13041822
10.3141/2554-13
10.3390/su12156027
10.3141/2278-08
10.1016/j.simpat.2021.102364
10.3390/su151411464
10.1007/s10462-021-09996-w
10.1016/j.aej.2020.11.005
10.2174/1874447800802010007
10.1109/TITS.2023.3285442
10.1061/9780784481530.018
10.1109/TSMCC.2007.913919
10.1177/0361198120949875
10.1177/0361198121997836
10.1109/ITSC45102.2020.9294639
10.3141/2470-13
10.1016/j.trb.2022.05.001
ContentType Journal Article
Copyright 2025 The Authors
Copyright_xml – notice: 2025 The Authors
DBID 6I.
AAFTH
AAYXX
CITATION
DOA
DOI 10.1016/j.aej.2024.12.110
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
DatabaseTitleList

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EndPage 115
ExternalDocumentID oai_doaj_org_article_1e503378295644f3a614e59f62485d87
10_1016_j_aej_2024_12_110
S1110016824017095
GroupedDBID --K
0R~
4.4
457
5VS
6I.
AACTN
AAEDT
AAEDW
AAFTH
AAIKJ
AALRI
AAXUO
ABMAC
ACGFS
ADBBV
ADEZE
ADVLN
AEXQZ
AFJKZ
AFTJW
AGHFR
AITUG
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
BCNDV
EBS
EJD
FDB
GROUPED_DOAJ
HZ~
IPNFZ
IXB
KQ8
M41
O-L
O9-
OK1
P2P
RIG
ROL
SES
SSZ
XH2
AAYWO
AAYXX
ACVFH
ADCNI
AEUPX
AFPUW
AIGII
AKBMS
AKYEP
CITATION
ID FETCH-LOGICAL-c406t-4738e929b02d260328d2ca53dd18a79fb33895df2f77983e4a44fa727fe051fe3
IEDL.DBID DOA
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001398208000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1110-0168
IngestDate Fri Oct 03 12:52:06 EDT 2025
Tue Nov 18 20:51:23 EST 2025
Wed Nov 12 18:32:29 EST 2025
Sat Apr 19 16:02:33 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords MADDPG
SUMO
Hard Shoulder Running
Spatial-temporal constrains
Highway
Language English
License This is an open access article under the CC BY-NC-ND license.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c406t-4738e929b02d260328d2ca53dd18a79fb33895df2f77983e4a44fa727fe051fe3
OpenAccessLink https://doaj.org/article/1e503378295644f3a614e59f62485d87
PageCount 17
ParticipantIDs doaj_primary_oai_doaj_org_article_1e503378295644f3a614e59f62485d87
crossref_citationtrail_10_1016_j_aej_2024_12_110
crossref_primary_10_1016_j_aej_2024_12_110
elsevier_sciencedirect_doi_10_1016_j_aej_2024_12_110
PublicationCentury 2000
PublicationDate April 2025
2025-04-00
2025-04-01
PublicationDateYYYYMMDD 2025-04-01
PublicationDate_xml – month: 04
  year: 2025
  text: April 2025
PublicationDecade 2020
PublicationTitle Alexandria engineering journal
PublicationYear 2025
Publisher Elsevier B.V
Elsevier
Publisher_xml – name: Elsevier B.V
– name: Elsevier
References Geistefeldt (bib7) 2024
Ministry of Transport of the People's Republic of China: JTG B01-2003, Technical Standard of Highway Engineering[S].
Lai, Dong, Andriotis, Wang, Lei (bib44) 2024; 160
Lu, Yi, Gu, Rui, Ran (bib16) 2023; 153
Kejriwal, Thomas (bib54) 2021; 112
Li, Ye, Li (bib2) 2017; 11
Li, Chow, Cassel (bib18) 2014; 2470
Ma, Hu, Hale, Bared (bib27) 2016; 2554
Chen, Hajidavalloo, Zhaojian (bib39) 2023; 24
Martinez-Gil, Lozano, Fernández (bib53) 2017; 74
Coffey, Park (bib19) 2018; 2018
Kolat, Kővári, Bécsi (bib42) 2023; 15
B. Lucian, B. Robert, D.S. BartA comprehensive survey of multiagent reinforcement learning, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 38(2); 156-1722008.
Wang, Lv, Jiang, Qin, Li (bib56) 2021; 584
S. Coffey, S. Park, Impact of part-time shoulder use on safety through the highway safety manual, International Conference on Transportation and Development 2018: Connected and Autonomous Vehicles and Transportation Safety, 2018, 180-187.
Fang, Péter, Tettamanti (bib40) 2023; 15
Aron, Seidowsky, Cohen (bib30) 2013; 28
K. Kušić, I. Dusparic, M. Guériau, M. Gregurić and E. Ivanjko Extended variable speed limit control using multi-agent reinforcement learning, in: 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), Rhodes, Greece (2020)1-8.
Mnih, Kavukcuoglu, Silver (bib51) 2015; 518
Z. Deng, Z. Luo, N. Hockaday, A. Farid, A. PandeEvaluation of left shoulder as part-time travel lane design alternatives and transportation management center staff training module development, 2023.
Yao, Qian, Feng, Zhang, Zhang, Chen, Meng (bib15) 2024
Lowe, Wu, Tamar, Harb, Abbeel, Mordatch (bib62) 2017; 30
Huang, Zhang, Zhang (bib50) 2021; 60
Zhou, Yang, Lee, Zhang (bib36) 2020; 2674
Geistefeldt (bib1) 2021
I. Shariq, F. Sha, Actor-attention-critic for multi-agent reinforcement learning, Proceedings of the 36th International Conference on Machine Learning 97(2019) 2961-2970.
Waleczek, Geistefeldt (bib29) 2021; 2675
Nguyen, Nguyen, Nahavandi (bib52) 2018; 50
Gronauer, Diepold (bib60) 2022; 55
Kononov, Hersey, Reeves, Allery (bib26) 2012; 2280
Sallab, Abdou, Perot, Yogamani (bib46) 2017; 29
Zheng, Ran, Qu (bib67) 2020; 21
M. Rohloff, Re-use of herd-shoulders at federal motorways, 2nd International Symposium on Highway Geometric Design, 2000, p. 254-266, Mainz, Germany.
B. Sultan, R. Meekums, J. Ogawa, S. Self, P. Unwin, M42 aCtive Traffic Management Pilot -- Initial Results from Hard Shoulder Running Under 60mph Speed Limit.
Z. Zhigang, P. Rui, Q. Jiangang, Analysis of traffic characteristics of dynamic open hard shoulder road based on SUMO, 2022 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI), Shijiazhuang, China, 2022, 100-104.
Jenior, P., Bonneson, J.A., Zhao, L., Kittelson, W., Donnell, E.T., & Gayah, V.V. Safety Performance of Part-time Shoulder Use on Freeways, Volume 1: Informational Guide and Safety Evaluation Guidelines, 2021.
LeCun, Bengio, Hinton (bib47) 2015; 521
Qian, Zhao, Huang (bib59) 2023; 621
Zhang, Lin, Li (bib58) 2023; 611
Geistefeldt (bib10) 2012; 2278
Zeng, Schrock (bib33) 2012; 2279
Hasan, Abdel-Aty (bib24) 2024; 199
Yang, Wang, Ding, Tan, Ran (bib38) 2021; 13
Li, Lasenby (bib23) 2023; 48
K. Lemke, Hard Shoulder Running as a short-term measure to reduce congestion, 4th International Symposium on Highway Geometric Design, 2010, Valencia, Spain.
S. Cohen, M. Aron, R. Seidowsky, Assessment of a dynamic managed lanes operation, 12 th WCTR, 2010, Lisbon.
Choi, Tay, Kim, Jeong, Kim, Heo (bib28) 2019; 9
Arora, Kattan (bib22) 2022
Sharma, Faruk, El-Urfali (bib34) 2020; 2674
Metaxatos, Thakuriah (bib3) 2009; 2111
Chasea, Avineri (bib31) 2008; 2
Xiaoming, Dong, Frangopol (bib43) 2023; 29
Drungilas, Kurmis, Senulis, Lukosius, Andziulis, Januteniene, Bogdevicius, Jankunas, Voznak (bib48) 2023; 67
Ying, Chow, Nguyen, Chin (bib45) 2022; 161
Zhang, Yang, Başar (bib61) 2021
Mnih, Kavukcuoglu, Silver (bib65) 2015; 518
Wilson (bib12) 2009; 78
M. Aron, S. Cohen, R. Seidowsky, Two French hard-shoulder running operations: some comments on effectiveness and safety, 13th International IEEE Conference on Intelligent Transportation Systems, Funchal, Portugal, 2010, 230-236.
Hussein, Naik, Süer (bib37) 2020
Martinez-Gil, Lozano, Fernández (bib55) 2014; 47
Li, Ye, Li (bib35) 2018; 30
Haarnoja, Zhou, Abbeel (bib66) 2018
Geistefeldt (bib17) 2012; 2278
Use of Freeway Shoulders for Travel — Guide for Planning, Evaluating, and Designing Part-time Shoulder Use as A Traffic Management Strategy
Mohammed H. Alabdullah, Mohammad A. Abido, Microgrid energy management using deep Q-network reinforcement learning, Alexandria Engineering Journal, 61(11)(202) 9069-9078.
2016.
S.G. Farrag, F. Outay, A. Yasar, M.Y. El-Hansali. Evaluating Active Traffic Management (ATM) Strategies under Non-recurring Congestion: Simulation-based with Benefit Cost Analysis Case Study. (2020).
Kellermann (bib9) 2000; 41
Yang (10.1016/j.aej.2024.12.110_bib38) 2021; 13
LeCun (10.1016/j.aej.2024.12.110_bib47) 2015; 521
Geistefeldt (10.1016/j.aej.2024.12.110_bib1) 2021
Coffey (10.1016/j.aej.2024.12.110_bib19) 2018; 2018
Qian (10.1016/j.aej.2024.12.110_bib59) 2023; 621
Mnih (10.1016/j.aej.2024.12.110_bib65) 2015; 518
Lu (10.1016/j.aej.2024.12.110_bib16) 2023; 153
Huang (10.1016/j.aej.2024.12.110_bib50) 2021; 60
Haarnoja (10.1016/j.aej.2024.12.110_bib66) 2018
Li (10.1016/j.aej.2024.12.110_bib35) 2018; 30
Fang (10.1016/j.aej.2024.12.110_bib40) 2023; 15
10.1016/j.aej.2024.12.110_bib32
Wilson (10.1016/j.aej.2024.12.110_bib12) 2009; 78
Kolat (10.1016/j.aej.2024.12.110_bib42) 2023; 15
Lai (10.1016/j.aej.2024.12.110_bib44) 2024; 160
Choi (10.1016/j.aej.2024.12.110_bib28) 2019; 9
Lowe (10.1016/j.aej.2024.12.110_bib62) 2017; 30
Chen (10.1016/j.aej.2024.12.110_bib39) 2023; 24
Hussein (10.1016/j.aej.2024.12.110_bib37) 2020
Sallab (10.1016/j.aej.2024.12.110_bib46) 2017; 29
Geistefeldt (10.1016/j.aej.2024.12.110_bib7) 2024
Gronauer (10.1016/j.aej.2024.12.110_bib60) 2022; 55
Waleczek (10.1016/j.aej.2024.12.110_bib29) 2021; 2675
Li (10.1016/j.aej.2024.12.110_bib23) 2023; 48
Metaxatos (10.1016/j.aej.2024.12.110_bib3) 2009; 2111
Geistefeldt (10.1016/j.aej.2024.12.110_bib17) 2012; 2278
10.1016/j.aej.2024.12.110_bib49
Nguyen (10.1016/j.aej.2024.12.110_bib52) 2018; 50
Arora (10.1016/j.aej.2024.12.110_bib22) 2022
Kellermann (10.1016/j.aej.2024.12.110_bib9) 2000; 41
10.1016/j.aej.2024.12.110_bib41
Geistefeldt (10.1016/j.aej.2024.12.110_bib10) 2012; 2278
Li (10.1016/j.aej.2024.12.110_bib18) 2014; 2470
Sharma (10.1016/j.aej.2024.12.110_bib34) 2020; 2674
Zheng (10.1016/j.aej.2024.12.110_bib67) 2020; 21
Wang (10.1016/j.aej.2024.12.110_bib56) 2021; 584
Ma (10.1016/j.aej.2024.12.110_bib27) 2016; 2554
Martinez-Gil (10.1016/j.aej.2024.12.110_bib53) 2017; 74
10.1016/j.aej.2024.12.110_bib8
Zeng (10.1016/j.aej.2024.12.110_bib33) 2012; 2279
10.1016/j.aej.2024.12.110_bib5
10.1016/j.aej.2024.12.110_bib6
Zhang (10.1016/j.aej.2024.12.110_bib58) 2023; 611
Zhang (10.1016/j.aej.2024.12.110_bib61) 2021
10.1016/j.aej.2024.12.110_bib4
Hasan (10.1016/j.aej.2024.12.110_bib24) 2024; 199
10.1016/j.aej.2024.12.110_bib14
Zhou (10.1016/j.aej.2024.12.110_bib36) 2020; 2674
10.1016/j.aej.2024.12.110_bib11
10.1016/j.aej.2024.12.110_bib13
10.1016/j.aej.2024.12.110_bib57
Aron (10.1016/j.aej.2024.12.110_bib30) 2013; 28
Yao (10.1016/j.aej.2024.12.110_bib15) 2024
Chasea (10.1016/j.aej.2024.12.110_bib31) 2008; 2
Ying (10.1016/j.aej.2024.12.110_bib45) 2022; 161
Kejriwal (10.1016/j.aej.2024.12.110_bib54) 2021; 112
Xiaoming (10.1016/j.aej.2024.12.110_bib43) 2023; 29
Drungilas (10.1016/j.aej.2024.12.110_bib48) 2023; 67
Martinez-Gil (10.1016/j.aej.2024.12.110_bib55) 2014; 47
Li (10.1016/j.aej.2024.12.110_bib2) 2017; 11
10.1016/j.aej.2024.12.110_bib25
10.1016/j.aej.2024.12.110_bib21
Mnih (10.1016/j.aej.2024.12.110_bib51) 2015; 518
Kononov (10.1016/j.aej.2024.12.110_bib26) 2012; 2280
10.1016/j.aej.2024.12.110_bib63
10.1016/j.aej.2024.12.110_bib20
10.1016/j.aej.2024.12.110_bib64
References_xml – volume: 2470
  start-page: 122
  year: 2014
  end-page: 130
  ident: bib18
  article-title: Optimal control of motorways by ramp metering, variable speed limits, and hard-shoulder running
  publication-title: Transp. Res. Rec.
– volume: 2674
  start-page: 282
  year: 2020
  end-page: 293
  ident: bib34
  article-title: Operational and safety impact analysis of implementing emergency shoulder use (ESU) for hurricane evacuation
  publication-title: Transp. Res. Rec.
– volume: 15
  start-page: 3479
  year: 2023
  ident: bib42
  article-title: Multi-agent reinforcement learning for traffic signal control: a cooperative approach
  publication-title: Sustainability
– volume: 47
  start-page: 259
  year: 2014
  end-page: 275
  ident: bib55
  article-title: MARL-Ped: a multi-agent reinforcement learning based framework to simulate pedestrian groups
  publication-title: Simul. Model. Pract. Theory
– reference: B. Sultan, R. Meekums, J. Ogawa, S. Self, P. Unwin, M42 aCtive Traffic Management Pilot -- Initial Results from Hard Shoulder Running Under 60mph Speed Limit.
– reference: Z. Zhigang, P. Rui, Q. Jiangang, Analysis of traffic characteristics of dynamic open hard shoulder road based on SUMO, 2022 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI), Shijiazhuang, China, 2022, 100-104.
– year: 2024
  ident: bib15
  article-title: Hidden markov model-based dynamic hard shoulders running strategy in hybrid network environments
  publication-title: Appl. Sci.
– volume: 2279
  start-page: 99
  year: 2012
  end-page: 107
  ident: bib33
  article-title: Estimation of safety effectiveness of composite shoulders on rural two-lane highways
  publication-title: Transp. Res. Rec.
– volume: 160
  year: 2024
  ident: bib44
  article-title: Synergetic-informed deep reinforcement learning for sustainable management of transportation networks with large action spaces
  publication-title: Autom. Constr.
– start-page: 41
  year: 2021
  end-page: 44
  ident: bib1
  article-title: Hard shoulder running
  publication-title: International Encyclopedia of Transportation
– reference: K. Kušić, I. Dusparic, M. Guériau, M. Gregurić and E. Ivanjko Extended variable speed limit control using multi-agent reinforcement learning, in: 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), Rhodes, Greece (2020)1-8.
– volume: 611
  year: 2023
  ident: bib58
  article-title: Graph attention reinforcement learning with flexible matching policies for multi-depot vehicle routing problems
  publication-title: Phys. A Stat. Mech. Appl.
– volume: 2278
  year: 2012
  ident: bib10
  article-title: Operational experience with temporary hard shoulder running in Germany
  publication-title: Transp. Res. Rec.
– volume: 2278
  start-page: 67
  year: 2012
  end-page: 73
  ident: bib17
  article-title: Operational experience with temporary hard shoulder running in Germany
  publication-title: Transp. Res. Rec.
– volume: 2675
  start-page: 345
  year: 2021
  end-page: 354
  ident: bib29
  article-title: Long-Term safety analysis of hard shoulder running on freeways in Germany
  publication-title: Transp. Res. Rec.
– reference: M. Rohloff, Re-use of herd-shoulders at federal motorways, 2nd International Symposium on Highway Geometric Design, 2000, p. 254-266, Mainz, Germany.
– volume: 50
  start-page: 3826
  year: 2018
  end-page: 3839
  ident: bib52
  article-title: Deep reinforcement learning for multi-agent systems: a review of challenges, solutions and applications
  publication-title: IEEE Trans. Cybern.
– year: 2020
  ident: bib37
  article-title: Development of hybrid hard shoulder running operation system for active traffic management
  publication-title: Int. Conf. Transp. Dev.
– reference: S. Cohen, M. Aron, R. Seidowsky, Assessment of a dynamic managed lanes operation, 12 th WCTR, 2010, Lisbon.
– volume: 15
  start-page: 11464
  year: 2023
  ident: bib40
  article-title: Variable speed limit control for the motorway–urban merging bottlenecks using multi-agent reinforcement learning
  publication-title: Sustainability
– reference: Jenior, P., Bonneson, J.A., Zhao, L., Kittelson, W., Donnell, E.T., & Gayah, V.V. Safety Performance of Part-time Shoulder Use on Freeways, Volume 1: Informational Guide and Safety Evaluation Guidelines, 2021.
– reference: Mohammed H. Alabdullah, Mohammad A. Abido, Microgrid energy management using deep Q-network reinforcement learning, Alexandria Engineering Journal, 61(11)(202) 9069-9078.
– year: 2021
  ident: bib61
  article-title: Multi-agent reinforcement learning: a selective overview of theories and algorithms
  publication-title: Handbook of Reinforcement Learning and Control. Studies in Systems, Decision and Control
– volume: 621
  year: 2023
  ident: bib59
  article-title: Model improvement and scheduling optimization for multi-vehicle charging planning in IoV
  publication-title: Phys. A Stat. Mech. Appl.
– year: 2024
  ident: bib7
  article-title: Operational reliability of hard shoulder running on freeways
  publication-title: Transp. Res. Rec.: J. Transp. Res. Board
– reference: K. Lemke, Hard Shoulder Running as a short-term measure to reduce congestion, 4th International Symposium on Highway Geometric Design, 2010, Valencia, Spain.
– volume: 584
  year: 2021
  ident: bib56
  article-title: A multi-agent based cellular automata model for intersection traffic control simulation
  publication-title: Phys. A Stat. Mech. Appl.
– volume: 112
  year: 2021
  ident: bib54
  article-title: A multi-agent simulator for generating novelty in monopoly
  publication-title: Simul. Model. Pract. Theory
– volume: 60
  start-page: 1509
  year: 2021
  end-page: 1517
  ident: bib50
  article-title: Energy management of intelligent building based on deep reinforced learning
  publication-title: Alex. Eng. J.
– reference: , 2016.
– volume: 29
  start-page: 04023063
  year: 2023
  ident: bib43
  article-title: Sustainable life-cycle maintenance policymaking for network-level deteriorating bridges with a convolutional autoencoder–structured reinforcement learning agent
  publication-title: J. Bridge Eng.
– reference: M. Aron, S. Cohen, R. Seidowsky, Two French hard-shoulder running operations: some comments on effectiveness and safety, 13th International IEEE Conference on Intelligent Transportation Systems, Funchal, Portugal, 2010, 230-236.
– volume: 518
  start-page: 529
  year: 2015
  end-page: 533
  ident: bib51
  article-title: Human-level control through deep reinforcement learning
  publication-title: Nature
– volume: 78
  start-page: 12
  year: 2009
  end-page: 13
  ident: bib12
  article-title: Hard shoulder running eases motorway traffic jams
  publication-title: Highways
– reference: Use of Freeway Shoulders for Travel — Guide for Planning, Evaluating, and Designing Part-time Shoulder Use as A Traffic Management Strategy,
– volume: 13
  start-page: 1822
  year: 2021
  ident: bib38
  article-title: Identify optimal traffic condition and speed limit for hard shoulder running strategy
  publication-title: Sustainability
– volume: 11
  start-page: 553
  year: 2017
  end-page: 560
  ident: bib2
  article-title: Simulation of hard shoulder running combined with queue warning during traffic accident with CTM model
  publication-title: IEEE Trans. Intell. Transp. Syst.
– reference: S. Coffey, S. Park, Impact of part-time shoulder use on safety through the highway safety manual, International Conference on Transportation and Development 2018: Connected and Autonomous Vehicles and Transportation Safety, 2018, 180-187.
– volume: 2280
  start-page: 10
  year: 2012
  end-page: 17
  ident: bib26
  article-title: Relationship between freeway flow parameters and safety and its implications for hard shoulder running
  publication-title: Transp. Res. Rec.
– start-page: 1861
  year: 2018
  end-page: 1870
  ident: bib66
  article-title: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor[C]//International conference on machine learning
  publication-title: PMLR
– year: 2022
  ident: bib22
  article-title: Operational and safety impacts of integrated variable speed limit with dynamic hard shoulder running
  publication-title: J. Intell. Transp. Syst.
– reference: Z. Deng, Z. Luo, N. Hockaday, A. Farid, A. PandeEvaluation of left shoulder as part-time travel lane design alternatives and transportation management center staff training module development, 2023.
– reference: I. Shariq, F. Sha, Actor-attention-critic for multi-agent reinforcement learning, Proceedings of the 36th International Conference on Machine Learning 97(2019) 2961-2970.
– reference: Ministry of Transport of the People's Republic of China: JTG B01-2003, Technical Standard of Highway Engineering[S].
– volume: 55
  start-page: 895
  year: 2022
  end-page: 943
  ident: bib60
  article-title: Multi-agent deep reinforcement learning: a survey
  publication-title: Artif. Intell. Rev.
– volume: 28
  start-page: 168
  year: 2013
  end-page: 180
  ident: bib30
  article-title: Safety impact of using the hard shoulder during congested traffic. The case of a managed lane operation on a French urban motorway
  publication-title: Transp. Res C. -Emer.
– volume: 161
  start-page: 36
  year: 2022
  end-page: 59
  ident: bib45
  article-title: Multi-agent deep reinforcement learning for adaptive coordinated metro service operations with flexible train composition
  publication-title: Transp. Res. Part B: Methodol.
– volume: 21
  start-page: 4605
  year: 2020
  end-page: 4614
  ident: bib67
  article-title: Cooperative lane changing strategies to improve traffic operation and safety nearby freeway off-ramps in a connected and automated vehicles environment
  publication-title: IEEE Trans. Intell. Transp. Syst.
– volume: 29
  start-page: 70
  year: 2017
  end-page: 79
  ident: bib46
  article-title: Deep reinforcement learning framework for Autonomous Driving
  publication-title: Electron. Imaging
– volume: 67
  start-page: 397
  year: 2023
  end-page: 407
  ident: bib48
  article-title: Deep reinforcement learning based optimization of automated guided vehicle time and energy consumption in a container terminal
  publication-title: Alex. Eng. J.
– volume: 2111
  start-page: 10
  year: 2009
  end-page: 17
  ident: bib3
  article-title: Planning for bus-on-shoulders operations in northeastern Illinois: a survey of stakeholders
  publication-title: Transp. Res. Rec.
– volume: 74
  start-page: 117
  year: 2017
  end-page: 133
  ident: bib53
  article-title: Emergent behaviors and scalability for multi-agent reinforcement learning-based pedestrian models
  publication-title: Simul. Model. Pract. Theory
– volume: 2018
  year: 2018
  ident: bib19
  article-title: Operational evaluation of part-time shoulder use for interstate 476 in the state of Pennsylvania
  publication-title: Adv. Civ. Eng.
– volume: 30
  start-page: 30
  year: 2017
  ident: bib62
  article-title: Multi-agent actor-critic for mixed cooperative-competitive environments
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 24
  start-page: 11623
  year: 2023
  end-page: 11638
  ident: bib39
  article-title: Deep multi-agent reinforcement learning for highway on-ramp merging in mixed traffic
  publication-title: IEEE Trans. Intell. Transp. Syst.
– volume: 199
  year: 2024
  ident: bib24
  article-title: Short-term safety performance functions by random parameters negative binomial-lindley model for part-time shoulder use
  publication-title: Accid. Anal. Prev.
– volume: 30
  start-page: 1036
  year: 2018
  end-page: 1045
  ident: bib35
  article-title: Optimal control and simulation of hard shoulder running on highways
  publication-title: J. Syst. Simul.
– reference: B. Lucian, B. Robert, D.S. BartA comprehensive survey of multiagent reinforcement learning, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 38(2); 156-1722008.
– volume: 518
  start-page: 529
  year: 2015
  end-page: 533
  ident: bib65
  article-title: Human-level control through deep reinforcement learning
  publication-title: Nature
– volume: 2674
  start-page: 915
  year: 2020
  end-page: 925
  ident: bib36
  article-title: Q-learning-based coordinated variable speed limit and hard shoulder running control strategy to reduce travel time at freeway corridor
  publication-title: Transp. Res. Rec.
– volume: 48
  year: 2023
  ident: bib23
  article-title: Mitigating urban motorway congestion and emissions via active traffic management
  publication-title: Res. Transp. Bus.
– reference: S.G. Farrag, F. Outay, A. Yasar, M.Y. El-Hansali. Evaluating Active Traffic Management (ATM) Strategies under Non-recurring Congestion: Simulation-based with Benefit Cost Analysis Case Study. (2020).
– volume: 2
  start-page: 7
  year: 2008
  end-page: 18
  ident: bib31
  article-title: Maximizing motorway capacity through hard shoulder running: UK perspective
  publication-title: Open Transp. J.
– volume: 41
  start-page: 10
  year: 2000
  ident: bib9
  article-title: Experience of using the hard shoulder to improve traffic flows
  publication-title: Traffic Eng. Control
– volume: 2554
  start-page: 120
  year: 2016
  end-page: 128
  ident: bib27
  article-title: Dynamic hard shoulder running for traffic incident management
  publication-title: Transp. Res. Rec.
– volume: 9
  start-page: 3614
  year: 2019
  ident: bib28
  article-title: Safety effects of freeway hard shoulder running
  publication-title: Appl. Sci.
– volume: 153
  year: 2023
  ident: bib16
  article-title: TD3LVSL: a lane-level variable speed limit approach based on twin delayed deep deterministic policy gradient in a connected automated vehicle environment
  publication-title: Transp. Res. Part C Emerg. Technol.
– volume: 521
  start-page: 436
  year: 2015
  end-page: 444
  ident: bib47
  article-title: Deep learning
  publication-title: Nature
– volume: 2111
  start-page: 10
  issue: 1
  year: 2009
  ident: 10.1016/j.aej.2024.12.110_bib3
  article-title: Planning for bus-on-shoulders operations in northeastern Illinois: a survey of stakeholders
  publication-title: Transp. Res. Rec.
  doi: 10.3141/2111-02
– volume: 29
  start-page: 04023063
  issue: 9
  year: 2023
  ident: 10.1016/j.aej.2024.12.110_bib43
  article-title: Sustainable life-cycle maintenance policymaking for network-level deteriorating bridges with a convolutional autoencoder–structured reinforcement learning agent
  publication-title: J. Bridge Eng.
– volume: 199
  year: 2024
  ident: 10.1016/j.aej.2024.12.110_bib24
  article-title: Short-term safety performance functions by random parameters negative binomial-lindley model for part-time shoulder use
  publication-title: Accid. Anal. Prev.
– year: 2021
  ident: 10.1016/j.aej.2024.12.110_bib61
  article-title: Multi-agent reinforcement learning: a selective overview of theories and algorithms
  doi: 10.1007/978-3-030-60990-0_12
– ident: 10.1016/j.aej.2024.12.110_bib8
  doi: 10.17226/26394
– year: 2020
  ident: 10.1016/j.aej.2024.12.110_bib37
  article-title: Development of hybrid hard shoulder running operation system for active traffic management
  publication-title: Int. Conf. Transp. Dev.
– volume: 29
  start-page: 70
  issue: 19
  year: 2017
  ident: 10.1016/j.aej.2024.12.110_bib46
  article-title: Deep reinforcement learning framework for Autonomous Driving
  publication-title: Electron. Imaging
  doi: 10.2352/ISSN.2470-1173.2017.19.AVM-023
– volume: 50
  start-page: 3826
  issue: 9
  year: 2018
  ident: 10.1016/j.aej.2024.12.110_bib52
  article-title: Deep reinforcement learning for multi-agent systems: a review of challenges, solutions and applications
  publication-title: IEEE Trans. Cybern.
  doi: 10.1109/TCYB.2020.2977374
– volume: 160
  year: 2024
  ident: 10.1016/j.aej.2024.12.110_bib44
  article-title: Synergetic-informed deep reinforcement learning for sustainable management of transportation networks with large action spaces
  publication-title: Autom. Constr.
  doi: 10.1016/j.autcon.2024.105302
– volume: 74
  start-page: 117
  year: 2017
  ident: 10.1016/j.aej.2024.12.110_bib53
  article-title: Emergent behaviors and scalability for multi-agent reinforcement learning-based pedestrian models
  publication-title: Simul. Model. Pract. Theory
  doi: 10.1016/j.simpat.2017.03.003
– ident: 10.1016/j.aej.2024.12.110_bib21
  doi: 10.1109/ICCEAI55464.2022.00029
– ident: 10.1016/j.aej.2024.12.110_bib6
– volume: 47
  start-page: 259
  year: 2014
  ident: 10.1016/j.aej.2024.12.110_bib55
  article-title: MARL-Ped: a multi-agent reinforcement learning based framework to simulate pedestrian groups
  publication-title: Simul. Model. Pract. Theory
  doi: 10.1016/j.simpat.2014.06.005
– volume: 584
  year: 2021
  ident: 10.1016/j.aej.2024.12.110_bib56
  article-title: A multi-agent based cellular automata model for intersection traffic control simulation
  publication-title: Phys. A Stat. Mech. Appl.
– ident: 10.1016/j.aej.2024.12.110_bib64
– volume: 15
  start-page: 3479
  year: 2023
  ident: 10.1016/j.aej.2024.12.110_bib42
  article-title: Multi-agent reinforcement learning for traffic signal control: a cooperative approach
  publication-title: Sustainability
  doi: 10.3390/su15043479
– ident: 10.1016/j.aej.2024.12.110_bib13
– volume: 30
  start-page: 1036
  issue: 3
  year: 2018
  ident: 10.1016/j.aej.2024.12.110_bib35
  article-title: Optimal control and simulation of hard shoulder running on highways
  publication-title: J. Syst. Simul.
– volume: 2279
  start-page: 99
  issue: 1
  year: 2012
  ident: 10.1016/j.aej.2024.12.110_bib33
  article-title: Estimation of safety effectiveness of composite shoulders on rural two-lane highways
  publication-title: Transp. Res. Rec.
  doi: 10.3141/2279-12
– volume: 621
  year: 2023
  ident: 10.1016/j.aej.2024.12.110_bib59
  article-title: Model improvement and scheduling optimization for multi-vehicle charging planning in IoV
  publication-title: Phys. A Stat. Mech. Appl.
– volume: 2674
  start-page: 282
  year: 2020
  ident: 10.1016/j.aej.2024.12.110_bib34
  article-title: Operational and safety impact analysis of implementing emergency shoulder use (ESU) for hurricane evacuation
  publication-title: Transp. Res. Rec.
  doi: 10.1177/0361198119900502
– volume: 28
  start-page: 168
  year: 2013
  ident: 10.1016/j.aej.2024.12.110_bib30
  article-title: Safety impact of using the hard shoulder during congested traffic. The case of a managed lane operation on a French urban motorway
  publication-title: Transp. Res C. -Emer.
  doi: 10.1016/j.trc.2010.12.006
– volume: 518
  start-page: 529
  year: 2015
  ident: 10.1016/j.aej.2024.12.110_bib65
  article-title: Human-level control through deep reinforcement learning
  publication-title: Nature
  doi: 10.1038/nature14236
– volume: 11
  start-page: 553
  issue: 9
  year: 2017
  ident: 10.1016/j.aej.2024.12.110_bib2
  article-title: Simulation of hard shoulder running combined with queue warning during traffic accident with CTM model
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1049/iet-its.2016.0345
– year: 2024
  ident: 10.1016/j.aej.2024.12.110_bib7
  article-title: Operational reliability of hard shoulder running on freeways
  publication-title: Transp. Res. Rec.: J. Transp. Res. Board
– start-page: 1861
  year: 2018
  ident: 10.1016/j.aej.2024.12.110_bib66
  article-title: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor[C]//International conference on machine learning
  publication-title: PMLR
– volume: 78
  start-page: 12
  issue: 1
  year: 2009
  ident: 10.1016/j.aej.2024.12.110_bib12
  article-title: Hard shoulder running eases motorway traffic jams
  publication-title: Highways
– volume: 153
  year: 2023
  ident: 10.1016/j.aej.2024.12.110_bib16
  article-title: TD3LVSL: a lane-level variable speed limit approach based on twin delayed deep deterministic policy gradient in a connected automated vehicle environment
  publication-title: Transp. Res. Part C Emerg. Technol.
– ident: 10.1016/j.aej.2024.12.110_bib49
  doi: 10.1016/j.aej.2022.02.042
– ident: 10.1016/j.aej.2024.12.110_bib14
– volume: 67
  start-page: 397
  year: 2023
  ident: 10.1016/j.aej.2024.12.110_bib48
  article-title: Deep reinforcement learning based optimization of automated guided vehicle time and energy consumption in a container terminal
  publication-title: Alex. Eng. J.
  doi: 10.1016/j.aej.2022.12.057
– volume: 21
  start-page: 4605
  issue: 11
  year: 2020
  ident: 10.1016/j.aej.2024.12.110_bib67
  article-title: Cooperative lane changing strategies to improve traffic operation and safety nearby freeway off-ramps in a connected and automated vehicles environment
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1109/TITS.2019.2942050
– volume: 9
  start-page: 3614
  year: 2019
  ident: 10.1016/j.aej.2024.12.110_bib28
  article-title: Safety effects of freeway hard shoulder running
  publication-title: Appl. Sci.
  doi: 10.3390/app9173614
– year: 2022
  ident: 10.1016/j.aej.2024.12.110_bib22
  article-title: Operational and safety impacts of integrated variable speed limit with dynamic hard shoulder running
  publication-title: J. Intell. Transp. Syst.
– ident: 10.1016/j.aej.2024.12.110_bib25
  doi: 10.1109/ITSC.2010.5625159
– volume: 2280
  start-page: 10
  issue: 1
  year: 2012
  ident: 10.1016/j.aej.2024.12.110_bib26
  article-title: Relationship between freeway flow parameters and safety and its implications for hard shoulder running
  publication-title: Transp. Res. Rec.
  doi: 10.3141/2280-02
– volume: 521
  start-page: 436
  year: 2015
  ident: 10.1016/j.aej.2024.12.110_bib47
  article-title: Deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– ident: 10.1016/j.aej.2024.12.110_bib4
– volume: 13
  start-page: 1822
  year: 2021
  ident: 10.1016/j.aej.2024.12.110_bib38
  article-title: Identify optimal traffic condition and speed limit for hard shoulder running strategy
  publication-title: Sustainability
  doi: 10.3390/su13041822
– volume: 48
  year: 2023
  ident: 10.1016/j.aej.2024.12.110_bib23
  article-title: Mitigating urban motorway congestion and emissions via active traffic management
  publication-title: Res. Transp. Bus.
– volume: 518
  start-page: 529
  year: 2015
  ident: 10.1016/j.aej.2024.12.110_bib51
  article-title: Human-level control through deep reinforcement learning
  publication-title: Nature
  doi: 10.1038/nature14236
– volume: 2554
  start-page: 120
  issue: 1
  year: 2016
  ident: 10.1016/j.aej.2024.12.110_bib27
  article-title: Dynamic hard shoulder running for traffic incident management
  publication-title: Transp. Res. Rec.
  doi: 10.3141/2554-13
– ident: 10.1016/j.aej.2024.12.110_bib20
  doi: 10.3390/su12156027
– volume: 2278
  issue: 1
  year: 2012
  ident: 10.1016/j.aej.2024.12.110_bib10
  article-title: Operational experience with temporary hard shoulder running in Germany
  publication-title: Transp. Res. Rec.
  doi: 10.3141/2278-08
– start-page: 41
  year: 2021
  ident: 10.1016/j.aej.2024.12.110_bib1
  article-title: Hard shoulder running
– volume: 2018
  year: 2018
  ident: 10.1016/j.aej.2024.12.110_bib19
  article-title: Operational evaluation of part-time shoulder use for interstate 476 in the state of Pennsylvania
  publication-title: Adv. Civ. Eng.
– volume: 112
  year: 2021
  ident: 10.1016/j.aej.2024.12.110_bib54
  article-title: A multi-agent simulator for generating novelty in monopoly
  publication-title: Simul. Model. Pract. Theory
  doi: 10.1016/j.simpat.2021.102364
– volume: 15
  start-page: 11464
  issue: 14
  year: 2023
  ident: 10.1016/j.aej.2024.12.110_bib40
  article-title: Variable speed limit control for the motorway–urban merging bottlenecks using multi-agent reinforcement learning
  publication-title: Sustainability
  doi: 10.3390/su151411464
– volume: 55
  start-page: 895
  year: 2022
  ident: 10.1016/j.aej.2024.12.110_bib60
  article-title: Multi-agent deep reinforcement learning: a survey
  publication-title: Artif. Intell. Rev.
  doi: 10.1007/s10462-021-09996-w
– volume: 60
  start-page: 1509
  issue: 1
  year: 2021
  ident: 10.1016/j.aej.2024.12.110_bib50
  article-title: Energy management of intelligent building based on deep reinforced learning
  publication-title: Alex. Eng. J.
  doi: 10.1016/j.aej.2020.11.005
– year: 2024
  ident: 10.1016/j.aej.2024.12.110_bib15
  article-title: Hidden markov model-based dynamic hard shoulders running strategy in hybrid network environments
  publication-title: Appl. Sci.
– volume: 2
  start-page: 7
  issue: 1
  year: 2008
  ident: 10.1016/j.aej.2024.12.110_bib31
  article-title: Maximizing motorway capacity through hard shoulder running: UK perspective
  publication-title: Open Transp. J.
  doi: 10.2174/1874447800802010007
– volume: 24
  start-page: 11623
  issue: 11
  year: 2023
  ident: 10.1016/j.aej.2024.12.110_bib39
  article-title: Deep multi-agent reinforcement learning for highway on-ramp merging in mixed traffic
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1109/TITS.2023.3285442
– ident: 10.1016/j.aej.2024.12.110_bib5
  doi: 10.1061/9780784481530.018
– volume: 41
  start-page: 10
  year: 2000
  ident: 10.1016/j.aej.2024.12.110_bib9
  article-title: Experience of using the hard shoulder to improve traffic flows
  publication-title: Traffic Eng. Control
– ident: 10.1016/j.aej.2024.12.110_bib57
  doi: 10.1109/TSMCC.2007.913919
– volume: 2674
  start-page: 915
  issue: 11
  year: 2020
  ident: 10.1016/j.aej.2024.12.110_bib36
  article-title: Q-learning-based coordinated variable speed limit and hard shoulder running control strategy to reduce travel time at freeway corridor
  publication-title: Transp. Res. Rec.
  doi: 10.1177/0361198120949875
– volume: 2675
  start-page: 345
  issue: 8
  year: 2021
  ident: 10.1016/j.aej.2024.12.110_bib29
  article-title: Long-Term safety analysis of hard shoulder running on freeways in Germany
  publication-title: Transp. Res. Rec.
  doi: 10.1177/0361198121997836
– ident: 10.1016/j.aej.2024.12.110_bib32
– ident: 10.1016/j.aej.2024.12.110_bib11
– volume: 2278
  start-page: 67
  issue: 1
  year: 2012
  ident: 10.1016/j.aej.2024.12.110_bib17
  article-title: Operational experience with temporary hard shoulder running in Germany
  publication-title: Transp. Res. Rec.
  doi: 10.3141/2278-08
– ident: 10.1016/j.aej.2024.12.110_bib41
  doi: 10.1109/ITSC45102.2020.9294639
– volume: 30
  start-page: 30
  issue: NIPS 2017
  year: 2017
  ident: 10.1016/j.aej.2024.12.110_bib62
  article-title: Multi-agent actor-critic for mixed cooperative-competitive environments
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 2470
  start-page: 122
  issue: 1
  year: 2014
  ident: 10.1016/j.aej.2024.12.110_bib18
  article-title: Optimal control of motorways by ramp metering, variable speed limits, and hard-shoulder running
  publication-title: Transp. Res. Rec.
  doi: 10.3141/2470-13
– ident: 10.1016/j.aej.2024.12.110_bib63
– volume: 611
  year: 2023
  ident: 10.1016/j.aej.2024.12.110_bib58
  article-title: Graph attention reinforcement learning with flexible matching policies for multi-depot vehicle routing problems
  publication-title: Phys. A Stat. Mech. Appl.
– volume: 161
  start-page: 36
  year: 2022
  ident: 10.1016/j.aej.2024.12.110_bib45
  article-title: Multi-agent deep reinforcement learning for adaptive coordinated metro service operations with flexible train composition
  publication-title: Transp. Res. Part B: Methodol.
  doi: 10.1016/j.trb.2022.05.001
SSID ssj0000579496
Score 2.355811
Snippet To alleviate traffic congestion and reduce vehicle emissions, the use of hard shoulder running (HSR) has emerged as a sustainable and cost-effective active...
SourceID doaj
crossref
elsevier
SourceType Open Website
Enrichment Source
Index Database
Publisher
StartPage 99
SubjectTerms Hard Shoulder Running
Highway
MADDPG
Spatial-temporal constrains
SUMO
Title Simulation optimization of highway hard shoulder running based on multi-agent deep deterministic policy gradient algorithm
URI https://dx.doi.org/10.1016/j.aej.2024.12.110
https://doaj.org/article/1e503378295644f3a614e59f62485d87
Volume 117
WOSCitedRecordID wos001398208000001&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  issn: 1110-0168
  databaseCode: DOA
  dateStart: 20100101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.doaj.org/
  omitProxy: false
  ssIdentifier: ssj0000579496
  providerName: Directory of Open Access Journals
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV09T8MwELUQYoAB8SnKlzwwIUUktps4IyAqpgoJkLpFTnxuU7VNlaZI8Os5O0mVBVhYMkROHJ3Punfx3XuE3DCj0lCoyPPxMz2htO-lKS6IBp5lqQw1j40Tm4iGQzkaxS8dqS9bE1bTA9eGuwvAHrRhHEMgL4ThCuMJ9GMTWi4uLV0fOaKeTjJVs3qjnzlxLtzLtvIqlO2RpivuUjDF3JAJ-yswsN2znaDkuPs7sakTbwYHZL8BivS-_sBDsgWLI7LXoQ88Jl-v-bxR36IFbv1501NJC0MdDbH6pLapiq4mVsgaSlqunUIRtbFLUxzp6gk9ZfurqAZY4qUuj3H8zXTpWIPpuHSFYRVVs3FR5tVkfkLeB09vj89eo6XgZRiyK09EXAJCodRnGlMYzqRmmepzrQOpotikmKrGfW2YiaJYchAKja0Q3BjAbWuAn5LtRbGAM0JxiA5sWwk3qRCAIR8xIst4IAKZRQA94rfGTLKGaNzqXcyStqJsmqD9E2v_JGCYg_g9crt5ZFmzbPw2-MGu0GagJch2N9BtksZtkr_cpkdEu75JgzVqDIGvyn-e-_w_5r4gu8yqCLv6n0uyXZVruCI72UeVr8pr58jfo9L1LA
linkProvider Directory of Open Access Journals
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=Simulation+optimization+of+highway+hard+shoulder+running+based+on+multi-agent+deep+deterministic+policy+gradient+algorithm&rft.jtitle=Alexandria+engineering+journal&rft.au=Hu%2C+Lipeng&rft.au=Tang%2C+Jinjun&rft.au=Zou%2C+Guoqing&rft.au=Li%2C+Zhitao&rft.date=2025-04-01&rft.issn=1110-0168&rft.volume=117&rft.spage=99&rft.epage=115&rft_id=info:doi/10.1016%2Fj.aej.2024.12.110&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_aej_2024_12_110
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1110-0168&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1110-0168&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1110-0168&client=summon