{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T22:26:48Z","timestamp":1780439208425,"version":"3.54.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tai.2024.3511513","type":"journal-article","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T14:24:09Z","timestamp":1733408649000},"page":"1114-1127","source":"Crossref","is-referenced-by-count":3,"title":["Improving String Stability in Cooperative Adaptive Cruise Control Through Multiagent Reinforcement Learning With Potential-Driven Motivation"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5507-4654","authenticated-orcid":false,"given":"Kun","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2564-7180","authenticated-orcid":false,"given":"Min","family":"Hua","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Birmingham, Birmingham, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1670-0015","authenticated-orcid":false,"given":"Xu","family":"He","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Birmingham, Birmingham, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6737-1381","authenticated-orcid":false,"given":"Lu","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9269-334X","authenticated-orcid":false,"given":"Changyin","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3263643"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3631613"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT58233.2024.10541039"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104525"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3084960"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3181002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI50040.2020.00013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3336670"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/s23104710"},{"key":"ref11","article-title":"Multi-agent reinforcement learning for connected and automated vehicles control: Recent advancements and future prospects","author":"Hua","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04866-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2023.121526"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2023.3298365"},{"key":"ref15","first-page":"456","article-title":"Learning correlated communication topology in multi-agent reinforcement learning","author":"Du","year":"2021","journal-title":"in Proc. 20th Int. Conf. Auton. Agents Multiagent Syst."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref17","first-page":"1","article-title":"VIF: Neighboring variational information flow for cooperative large-scale multiagent reinforcement learning","author":"Zhu","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref18","article-title":"Multi-agent reinforcement learning for networked system control","author":"Chu","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3368025"},{"issue":"132","key":"ref20","first-page":"1","article-title":"An optimization-centric view on Bayes\u2019 rule: Reviewing and generalizing variational inference","volume":"23","author":"Knoblauch","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2024.124281"},{"key":"ref22","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Omidshafiei","year":"2017"},{"key":"ref23","first-page":"73898","article-title":"Dual self-awareness value decomposition framework without individual global max for cooperative MARL","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xu","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4152195"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref29","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref30","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref31","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn., ser. Proc. Mach. Learn. Res.","volume":"48,","author":"Mnih","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030110"},{"key":"ref33","first-page":"1","article-title":"Heterogeneous-agent reinforcement learning","volume":"25","author":"Zhong","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","first-page":"7787","article-title":"Challenges and opportunities in high dimensional variational inference","volume":"34","author":"Dhaka","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"28","key":"ref35","first-page":"1","article-title":"Additive smoothing error in backward variational inference for general state-space models","volume":"25","author":"Chagneux","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3173923"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.1035"},{"key":"ref38","volume-title":"Numerical Analysis","author":"Burden","year":"2015"},{"key":"ref39","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Foerster","year":"2017"},{"key":"ref40","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume":"29","author":"Sukhbaatar","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref41","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Zhang","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103047"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/10980621\/10778266.pdf?arnumber=10778266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T19:01:16Z","timestamp":1764270076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10778266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":42,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3511513","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}