{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T13:37:46Z","timestamp":1768311466297,"version":"3.49.0"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"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":[[2025,11,24]]},"DOI":"10.1109\/dsa66321.2025.00044","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:20:20Z","timestamp":1768242020000},"page":"311-320","source":"Crossref","is-referenced-by-count":0,"title":["A Survey of Cooperative Decision-Making in Autonomous Vehicle Platooning Based on Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Wenjing","family":"Zhong","sequence":"first","affiliation":[{"name":"School of Computer Engineering, Hubei University of Arts and Science,China"}]},{"given":"Xiaohu","family":"Tu","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Hubei University of Arts and Science,China"}]},{"given":"Wei","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Hubei University of Arts and Science,China"}]},{"given":"Xinying","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Hubei University of Arts and Science,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2015.2471046"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2019.03.001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.70003\/160792642025052603002"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.70003\/160792642024112506009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23940\/ijpe.25.06.p6.339350"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/s23104710"},{"issue":"1","key":"ref7","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3616864"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2016.04.008"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2865546"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2682421"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2023.01.012"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2021.3131305"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123507"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3004573"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3046165"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3025729"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022633531479"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref20","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv preprint arXiv"},{"issue":"178","key":"ref21","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3172572"},{"key":"ref23","article-title":"Multi-agent actor-critic for mixed cooperativecompetitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"12208","article-title":"Facmac: Factored multi-agent centralised policy gradients","volume":"34","author":"Peng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref26","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"29","author":"Foerster","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"12843","article-title":"Deconfounded value decomposition for multiagent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Li","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103744"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.trd.2025.104658"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI50040.2020.00013"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3368025"},{"key":"ref32","article-title":"Decentralized cooperative lane changing at freeway weaving areas using multi-agent deep reinforcement learning","author":"Hou","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285442"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12702"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IV64158.2025.11097808"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/wevj16040225"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/itsc58415.2024.10920154"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/su16229646"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10015-025-01056-8"},{"key":"ref40","first-page":"25667","article-title":"Safebench: A benchmarking platform for safety evaluation of autonomous vehicles","volume":"35","author":"Xu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s44172-024-00292-3"},{"key":"ref42","article-title":"Learning control barrier functions and their application in reinforcement learning: A survey","author":"Guerrier","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"A survey of constraint formulations in safe reinforcement learning","author":"Wachi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.14722\/vehiclesec.2024.23035"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104389"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/23249935.2024.2407077"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2024.106046"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2023.102739"},{"key":"ref49","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588385"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89378-3_37"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12440"},{"key":"ref53","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760239"},{"key":"ref55","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"International conference on machine learning","author":"Yang","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3090855"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ITST.2011.6060086"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref61","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning","author":"Achiam","year":"2017"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"}],"event":{"name":"2025 12th International Conference on Dependable Systems and Their Applications (DSA)","location":"Sharjah, United Arab Emirates","start":{"date-parts":[[2025,11,24]]},"end":{"date-parts":[[2025,11,26]]}},"container-title":["2025 12th International Conference on Dependable Systems and Their Applications (DSA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11320275\/11320347\/11320414.pdf?arnumber=11320414","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:16:41Z","timestamp":1768292201000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11320414\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/dsa66321.2025.00044","relation":{},"subject":[],"published":{"date-parts":[[2025,11,24]]}}}