{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:41:24Z","timestamp":1778258484153,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,24]]},"DOI":"10.1109\/itsc58415.2024.10919506","type":"proceedings-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T19:00:11Z","timestamp":1742583611000},"page":"776-783","source":"Crossref","is-referenced-by-count":7,"title":["Field Deployment of Multi-Agent Reinforcement Learning Based Variable Speed Limit Controllers"],"prefix":"10.1109","author":[{"given":"Yuhang","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute for Software Integrated Systems, Vanderbilt University,Nashville,TN,USA,37212"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute for Software Integrated Systems, Vanderbilt University,Nashville,TN,USA,37212"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcos","family":"Qui\u00f1ones-Grueiro","sequence":"additional","affiliation":[{"name":"Institute for Software Integrated Systems, Vanderbilt University,Nashville,TN,USA,37212"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Barbour","sequence":"additional","affiliation":[{"name":"Institute for Software Integrated Systems, Vanderbilt University,Nashville,TN,USA,37212"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Clay","family":"Weston","sequence":"additional","affiliation":[{"name":"Southwest Research Institute,San Antonio,TX,USA,78238"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gautam","family":"Biswas","sequence":"additional","affiliation":[{"name":"Institute for Software Integrated Systems, Vanderbilt University,Nashville,TN,USA,37212"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Work","sequence":"additional","affiliation":[{"name":"Institute for Software Integrated Systems, Vanderbilt University,Nashville,TN,USA,37212"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3141\/2423-03"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1179\/1942787514Y.0000000053"},{"key":"ref3","article-title":"Variable speed limit (vsl)-best management practice","author":"Elefteriadou","year":"2012","journal-title":"tech. rep., University of Florida. Transportation Research Center"},{"key":"ref4","volume-title":"Examples of variable speed limit applications: Speed management workshop","author":"Robinson","year":"2000"},{"key":"ref5","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app10144917"},{"issue":"AP-R342\/09","key":"ref7","author":"Han","year":"2009","journal-title":"Best practice for variable speed limits: Literature review"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3141\/2047-05"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2017.06.013"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922471"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2009.05.014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CP.1943-5487.0000790"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2008.4732611"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2010.5624974"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1061\/(asce)te.1943-5436.0000895"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2687620"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102649"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2904619"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/4419907"},{"key":"ref20","article-title":"Marvel: Multi-agent reinforcement-learning for large-scale variable speed limits","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.02.005"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3302509.3313784"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA51439.2020.9264552"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811912"},{"key":"ref25","article-title":"Reinforcement learning based oscillation dampening: Scaling up single-agent r1 algorithms to a 100 av highway field operational test","author":"Jang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP58114.2023.00036"},{"key":"ref27","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Yu","year":"2022"},{"key":"ref28","article-title":"U.S. Department of Transportation, Federal Highway Administration","volume-title":"Manual on Uniform Traffic Control Devices","year":"2009"},{"key":"ref29","article-title":"A closer look at invalid action masking in policy gradient algorithms","author":"Huang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"104311","DOI":"10.1016\/j.trc.2023.104311","article-title":"I-24 motion: An instrument for freeway traffic science","volume":"155","author":"Gloudemans","year":"2023","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"ref31","author":"Van Geffen","year":"2022","journal-title":"System architecture for ai-enabled corridor management"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FISTS60717.2024.10485593"},{"issue":"78","key":"ref33","first-page":"1","article-title":"Pot: Python optimal transport","volume":"22","author":"Flamary","year":"2021","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)","location":"Edmonton, AB, Canada","start":{"date-parts":[[2024,9,24]]},"end":{"date-parts":[[2024,9,27]]}},"container-title":["2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10919469\/10919190\/10919506.pdf?arnumber=10919506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T21:45:54Z","timestamp":1742593554000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10919506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,24]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/itsc58415.2024.10919506","relation":{},"subject":[],"published":{"date-parts":[[2024,9,24]]}}}