{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T14:47:58Z","timestamp":1776437278681,"version":"3.51.2"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000140","name":"U.S. Department of Transportation","doi-asserted-by":"publisher","award":["693JJ22140000Z44ATNREG3202"],"award-info":[{"award-number":["693JJ22140000Z44ATNREG3202"]}],"id":[{"id":"10.13039\/100000140","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2135579"],"award-info":[{"award-number":["CNS-2135579"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3489474","type":"journal-article","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:35:59Z","timestamp":1730396159000},"page":"161995-162014","source":"Crossref","is-referenced-by-count":11,"title":["MARVEL: Bringing Multi-Agent Reinforcement- Learning Based Variable Speed Limit Controllers Closer to Deployment"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8408-2095","authenticated-orcid":false,"given":"Yuhang","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute for Software Integrated Systems, Vanderbilt University, Nashville, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5391-6774","authenticated-orcid":false,"given":"Marcos","family":"Quinones-Grueiro","sequence":"additional","affiliation":[{"name":"Institute for Software Integrated Systems, Vanderbilt University, Nashville, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute for Software Integrated Systems, Vanderbilt University, Nashville, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3988-8356","authenticated-orcid":false,"given":"Yanbing","family":"Wang","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1368-3192","authenticated-orcid":false,"given":"William","family":"Barbour","sequence":"additional","affiliation":[{"name":"Institute for Software Integrated Systems, Vanderbilt University, Nashville, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2752-3878","authenticated-orcid":false,"given":"Gautam","family":"Biswas","sequence":"additional","affiliation":[{"name":"Institute for Software Integrated Systems, Vanderbilt University, Nashville, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0565-2158","authenticated-orcid":false,"given":"Daniel","family":"Work","sequence":"additional","affiliation":[{"name":"Institute for Software Integrated Systems, Vanderbilt University, Nashville, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/15472450490492851"},{"key":"ref2","article-title":"ITS field demonstration: Integration of variable speed limit control and travel time estimation for a recurrently congested highway","volume-title":"Proc. 91st Transp. Res. Board Annu. Meeting","author":"Chang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3141\/2423-03"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1179\/1942787514Y.0000000053"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2007.908562"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2016.01.001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2014.01.014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2904619"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103900"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3141730"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102618"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adg1462"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2687620"},{"key":"ref14","article-title":"Differential variable speed limits control for freeway recurrent bottlenecks via deep reinforcement learning","author":"Wu","year":"2018","journal-title":"arXiv:1810.10952"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/4419907"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/su151411464"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564739"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294639"},{"key":"ref19","volume-title":"Manual Uniform Traffic Control Devices","year":"2009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19940444"},{"key":"ref21","article-title":"Control by variable speed signs: The Dutch experiment","volume-title":"Proc. Int. Conf. Road Traffic Monitor. Control (6th: London, England). 6th Int. Conf. Road Traffic Monitor. Control","author":"Smulders"},{"key":"ref22","volume-title":"M25 controlled motorways: Summary report","author":"Agency","year":"2004"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3141\/1689-08"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/0361198106197800119"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3141\/2380-07"},{"key":"ref26","article-title":"Examples of variable speed limit applications: Speed management workshop","volume-title":"Proc. 79th Transp. Res. Board Annu. Meeting","author":"Robinson"},{"key":"ref27","volume-title":"Variable speed limit (VSL)-best management practice","author":"Elefteriadou","year":"2012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2961699"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922471"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP58114.2023.00036"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2017.06.013"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2005.10.010"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2014.05.016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2006.1657497"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2331985"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2374167"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2009.05.014"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2156792"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/99769"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1287\/opre.4.1.42"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1137\/S0036139997332099"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2004.08.001"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2002.806804"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2004.842408"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.02.009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2971663"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CP.1943-5487.0000790"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.1090.0314"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/app10144917"},{"issue":"8","key":"ref50","first-page":"1","article-title":"Decentralised reinforcement learning for ramp metering and variable speed limits on highways","volume":"14","author":"Schmidt-Dumont","year":"2015","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102649"},{"key":"ref52","volume-title":"Multi-Agent Reinforcement Learning: Foundations and Modern Approaches","author":"Albrecht","year":"2024"},{"key":"ref53","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref54","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Foerster"},{"key":"ref55","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"issue":"1","key":"ref56","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref57","article-title":"An introduction to centralized training for decentralized execution in cooperative multi-agent reinforcement learning","author":"Amato","year":"2024","journal-title":"arXiv:2409.03052"},{"key":"ref58","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Schulman"},{"key":"ref59","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Yu"},{"key":"ref60","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013796"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09552-y"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v35i.130584"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3182\/20090902-3-US-2007.0073"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/S0968-090X(96)00006-X"},{"key":"ref66","volume-title":"Synthesis of variable speed limit signs","author":"Katz","year":"2017"},{"key":"ref67","volume-title":"Modeling drivers\u2019 acceleration and lane changing behavior","author":"Ahmed","year":"1999"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104311"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/10380310\/10740279-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10740279.pdf?arnumber=10740279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T06:27:03Z","timestamp":1732688823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10740279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3489474","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}