{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:02:55Z","timestamp":1783530175805,"version":"3.55.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tits.2023.3285442","type":"journal-article","created":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T02:58:19Z","timestamp":1687575499000},"page":"11623-11638","source":"Crossref","is-referenced-by-count":210,"title":["Deep Multi-Agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0551-5084","authenticated-orcid":false,"given":"Dong","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Michigan State University, Lansing, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8880-9098","authenticated-orcid":false,"given":"Mohammad R.","family":"Hajidavalloo","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Michigan State University, Lansing, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0189-8719","authenticated-orcid":false,"given":"Zhaojian","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Michigan State University, Lansing, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3405-1389","authenticated-orcid":false,"given":"Kaian","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Michigan State University, Lansing, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8600-0276","authenticated-orcid":false,"given":"Yongqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6458-6886","authenticated-orcid":false,"given":"Longsheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Clemson University, Clemson, SC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0146-7262","authenticated-orcid":false,"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Clemson University, Clemson, SC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Future of Driving","year":"2021"},{"key":"ref2","volume-title":"Apollo Open Platform","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0168054"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0184952"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.apm.2005.02.008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbspro.2011.04.505"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.11.007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2015.2503342"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2600504"},{"key":"ref10","first-page":"17","volume-title":"Real-Time Metering Algorithm for Centralized Control","volume":"1232","author":"Jacobson","year":"1989"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3141\/1811-03"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304647"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2014.10.005"},{"key":"ref14","volume-title":"Model Predictive Control: Theory, Computation, and Design","author":"Rawlings","year":"2017"},{"issue":"12","key":"ref15","doi-asserted-by":"crossref","first-page":"2043","DOI":"10.1109\/JPROC.2003.819610","article-title":"Review of road traffic control strategies","volume":"91","author":"Papageorgiou","year":"2003","journal-title":"Proc. IEEE"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2002.806803"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2007.908724"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2285337"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbspro.2013.05.036"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3114983"},{"key":"ref21","article-title":"Combining reinforcement learning with model predictive control for on-ramp merging","author":"Lubars","year":"2020","journal-title":"arXiv:2011.08484"},{"key":"ref22","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref23","first-page":"1","article-title":"Multi-agent graph reinforcement learning for connected automated driving","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"key":"ref25","article-title":"Parameter sharing reinforcement learning architecture for multi agent driving behaviors","author":"Kaushik","year":"2018","journal-title":"arXiv:1811.07214"},{"key":"ref26","article-title":"Leveraging the capabilities of connected and autonomous vehicles and multi-agent reinforcement learning to mitigate highway bottleneck congestion","author":"Young Joun Ha","year":"2020","journal-title":"arXiv:2010.05436"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47358-7_7"},{"key":"ref28","article-title":"A DRL-based multiagent cooperative control framework for CAV networks: A graphic convolution Q network","author":"Dong","year":"2020","journal-title":"arXiv:2010.05437"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2893683"},{"key":"ref30","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref31","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref33","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3051163"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tpwrs.2021.3100898"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref37","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"ref39","article-title":"Revisiting parameter sharing in multi-agent deep reinforcement learning","author":"Terry","year":"2021","journal-title":"arXiv:2005.13625"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref41","article-title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","author":"Wu","year":"2017","journal-title":"arXiv:1708.05144"},{"key":"ref42","article-title":"Safe multi-agent reinforcement learning via shielding","author":"Elsayed-Aly","year":"2021","journal-title":"arXiv:2101.11196"},{"key":"ref43","article-title":"Safe multi-agent reinforcement learning through decentralized multiple control barrier functions","author":"Cai","year":"2021","journal-title":"arXiv:2103.12553"},{"key":"ref44","article-title":"Deep recurrent Q-learning for partially observable MDPs","author":"Hausknecht","year":"2015","journal-title":"arXiv:1507.06527"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2017-5099"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147626"},{"key":"ref47","volume-title":"A Policy on Geometric Design of Highways and Streets","year":"2001"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3141\/2088-10"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2001.948767"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916924"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995816"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1142\/9789812777263_0020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6220"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref57","first-page":"91","article-title":"On local rewards and scaling distributed reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"18","author":"Bagnell"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v35i.130584"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/MDM.2009.127"},{"key":"ref61","volume-title":"An Environment for Autonomous Driving Decision-Making","year":"2018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500718"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s10015-012-0059-8"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01327"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.01955"},{"key":"ref66","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.3012947"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197132"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"issue":"42","key":"ref70","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garcia","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6979\/10304348\/10159552-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10304348\/10159552.pdf?arnumber=10159552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T02:25:43Z","timestamp":1710383143000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10159552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":71,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tits.2023.3285442","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}