{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:19:38Z","timestamp":1784906378749,"version":"3.55.0"},"reference-count":182,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3574280","type":"journal-article","created":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T18:14:10Z","timestamp":1748456050000},"page":"16266-16286","source":"Crossref","is-referenced-by-count":64,"title":["Multi-Agent Reinforcement Learning for Connected and Automated Vehicles Control: Recent Advancements and Future Prospects"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2564-7180","authenticated-orcid":false,"given":"Min","family":"Hua","sequence":"first","affiliation":[{"name":"School of Engineering, University of Birmingham, Birmingham, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1454-4634","authenticated-orcid":false,"given":"Xinda","family":"Qi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0551-5084","authenticated-orcid":false,"given":"Dong","family":"Chen","sequence":"additional","affiliation":[{"name":"Agricultural and Biological Engineering, Mississippi State University, Starkville, MS, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5507-4654","authenticated-orcid":false,"given":"Kun","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1774-647X","authenticated-orcid":false,"given":"Zemin Eitan","family":"Liu","sequence":"additional","affiliation":[{"name":"Chemical and Petroleum Engineering Department, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyu","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Birmingham, Birmingham, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4216-3468","authenticated-orcid":false,"given":"Quan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Birmingham, Birmingham, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7241-8383","authenticated-orcid":false,"given":"Hongming","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Birmingham, Birmingham, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3228397"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3239748"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2023.3325403"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1504\/IJVAS.2020.104818"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.47852\/bonviewjcce2202245"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0954407017751788"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.3012947"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3162038"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3368025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3307002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3170308"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3175040"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3417387"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2023.3240430"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2024.3363650"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3121985"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2942014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3503092"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2022.2109416"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3447039"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3231845"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3190901"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3293198"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-51497-5_4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.geits.2024.100156"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3336670"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3233\/AIC-220316"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104919"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285442"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3270489"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3377291"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/s23104710"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref35","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.02.037"},{"key":"ref38","first-page":"7611","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahajan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2023.02.015"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2022.3217922"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3435036"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801701"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3335597"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030110"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref47","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref49","first-page":"28701","article-title":"Policy regularization with dataset constraint for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ran"},{"key":"ref50","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3342559"},{"key":"ref52","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rashid"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413114"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17348"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3172572"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3262921"},{"key":"ref57","first-page":"2402","article-title":"MA-MIX: Value function decomposition for cooperative multiagent reinforcement learning based on multi-head attention mechanism","volume-title":"Proc. 23rd Int. Conf. Auto. Agents Multiagent Syst.","author":"Niu"},{"key":"ref58","first-page":"1","article-title":"Multi-agent reinforcement learning for networked system control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chu"},{"key":"ref59","first-page":"9908","article-title":"Learning efficient multi-agent communication: An information bottleneck approach","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref60","article-title":"Verco: Learning coordinated verbal communication for multi-agent reinforcement learning","author":"Li","year":"2024","journal-title":"arXiv:2404.17780"},{"key":"ref61","article-title":"Asynchronous cooperative multi-agent reinforcement learning with limited communication","author":"Dolan","year":"2025","journal-title":"arXiv:2502.00558"},{"key":"ref62","article-title":"Hierarchical cooperative multi-agent reinforcement learning with skill discovery","author":"Yang","year":"2019","journal-title":"arXiv:1912.03558"},{"key":"ref63","article-title":"RODE: Learning roles to decompose multi-agent tasks","author":"Wang","year":"2020","journal-title":"arXiv:2010.01523"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892666"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26386"},{"key":"ref66","first-page":"1","article-title":"Hierarchical multi-agent skill discovery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165114"},{"key":"ref68","first-page":"12843","article-title":"Deconfounded value decomposition for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref69","article-title":"Discovering causality for efficient cooperation in multi-agent environments","author":"Pina","year":"2023","journal-title":"arXiv:2306.11846"},{"key":"ref70","first-page":"21937","article-title":"Lazy agents: A new perspective on solving sparse reward problem in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106101"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04866-0"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3020400"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2023.3268076"},{"key":"ref76","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. AAMAS","author":"Sunehag"},{"key":"ref77","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Son"},{"key":"ref78","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref79","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Foerster"},{"key":"ref80","first-page":"1","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11831"},{"key":"ref83","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Vezhnevets"},{"key":"ref84","first-page":"1","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nachum"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref86","article-title":"Causal multi-agent reinforcement learning: Review and open problems","author":"John Grimbly","year":"2021","journal-title":"arXiv:2111.06721"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3176182"},{"key":"ref88","volume-title":"Intrinsic Social Motivation Via Causal Influence in Multi-agent RL","author":"Jaques","year":"2018"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.02.009"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICHMS53169.2021.9582667"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00039"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3164656"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104019"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3259688"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13153102"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3415660"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922266"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3216288"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/s43684-022-00023-5"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121242"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588529"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3317957"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2577499"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3240425"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2911607"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1049\/itr2.12386"},{"key":"ref107","article-title":"Emergence of locomotion behaviours in rich environments","author":"Heess","year":"2017","journal-title":"arXiv:1707.02286"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/vtc2022-spring54318.2022.9860518"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2019.03.001"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI50040.2020.00013"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071959"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3165178"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2023.110854"},{"key":"ref115","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu"},{"key":"ref116","article-title":"Decentralized cooperative lane changing at freeway weaving areas using multi-agent deep reinforcement learning","author":"Hou","year":"2021","journal-title":"arXiv:2110.08124"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3275582"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3258685"},{"key":"ref119","article-title":"A multi-agent reinforcement learning approach for safe and efficient behavior planning of connected autonomous vehicles","author":"Han","year":"2020","journal-title":"arXiv:2003.04371"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12702"},{"key":"ref123","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":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3047129"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.04.012"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2904742"},{"key":"ref127","first-page":"21","article-title":"Coordinated deep reinforcement learners for traffic light control","volume-title":"Proc. Learn., Inference Control Multi-Agent Syst. (NIPS)","volume":"8","author":"Van der Pol"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104165"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103046"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2997896"},{"key":"ref131","first-page":"816","article-title":"Feudal multi-agent deep reinforcement learning for traffic signal control","volume-title":"Proc. 19th Int. Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Ma"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-024-09644-x"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-36606-2"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3033782"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/535"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.3390\/s23198229"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.015"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3169907"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3413356"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3321346"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8916951"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922173"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.23919\/acc53348.2022.9867314"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968478"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3144516"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186792"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565085"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2016.7795648"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575135"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565000"},{"key":"ref152","article-title":"Implicit multiagent coordination at unsignalized intersections via multimodal inference enabled by topological braids","author":"Mavrogiannis","year":"2020","journal-title":"arXiv:2004.05205"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10001133"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565126"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3054649"},{"key":"ref156","article-title":"Reinforcement learning aided sequential optimization for unsignalized intersection management of robot traffic","author":"Hoysal","year":"2023","journal-title":"arXiv:2302.05082"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2021-Fall52928.2021.9625057"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3219428"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3314139"},{"key":"ref161","article-title":"SMARTS: Scalable multi-agent reinforcement learning training school for autonomous driving","author":"Zhou","year":"2020","journal-title":"arXiv:2010.09776"},{"key":"ref162","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","volume":"78","author":"Dosovitskiy"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2919470"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827451"},{"key":"ref166","first-page":"3962","article-title":"Nocturne: A scalable driving benchmark for bringing multi-agent learning one step closer to the real world","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vinitsky"},{"key":"ref167","volume-title":"An Environment for Autonomous Driving Decision-making","author":"Leurent","year":"2018"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3457538"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06187-8"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103905"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3224984"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102887"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3216000"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/OJITS.2022.3172981"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6205"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10348-5"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28016-0_24"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1177\/0954407019856153"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3277015"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1016\/j.rineng.2022.100677"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3162651"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3463407"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/11016811.pdf?arnumber=11016811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T05:50:27Z","timestamp":1749793827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11016811\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":182,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3574280","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}