{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:12:34Z","timestamp":1740132754223,"version":"3.37.3"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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. Veh. Technol."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tvt.2024.3424191","type":"journal-article","created":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T17:18:34Z","timestamp":1720199914000},"page":"16076-16091","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Agent Probabilistic Ensembles With Trajectory Sampling for Connected Autonomous Vehicles"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7414-5638","authenticated-orcid":false,"given":"Ruoqi","family":"Wen","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-5060","authenticated-orcid":false,"given":"Rongpeng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1780-2547","authenticated-orcid":false,"given":"Guoru","family":"Ding","sequence":"additional","affiliation":[{"name":"College of Communications and Engineering, Army Engineering University of PLA, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5479-7890","authenticated-orcid":false,"given":"Zhifeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps58843.2023.10464651"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"article-title":"Multi-agent reinforcement learning for connected and automated vehicles control: Recent advancements and future prospects","year":"2023","author":"Hua","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890726"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3177685"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2498841"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3026111"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3216288"},{"key":"ref10","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Lowe","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"issue":"1","key":"ref12","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3312574"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3185159"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.102987"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.strusafe.2008.06.020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref19","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NIPS)","author":"Chua","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref21","first-page":"19580","article-title":"Efficient model-based multi-agent reinforcement learning via optimistic equilibrium computation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Sessa","year":"2022"},{"article-title":"Transfer in reinforcement learning via regret bounds for learning agents","year":"2022","author":"Tuynman","key":"ref22"},{"key":"ref23","first-page":"4863","article-title":"Is Q-learning provably efficient?","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","author":"Jin","year":"2018"},{"key":"ref24","first-page":"15198","article-title":"Almost optimal model-free reinforcement learningvia reference-advantage decomposition","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","author":"Zhang","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/37.845037"},{"volume-title":"Model Predictive Control: Theory, Computation, and Design","year":"2017","author":"Rawlings","key":"ref26"},{"issue":"2","key":"ref27","first-page":"109","article-title":"The complexity of generalized clique covering","volume-title":"Discrete Appl. Math.","volume":"22","author":"Corneil","year":"1988"},{"key":"ref28","first-page":"264","article-title":"SMARTS: An open-source scalable multi-agent RL training school for autonomous driving","volume-title":"Proc. Mach. Learn. Res.","author":"Zhou","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564518"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3169907"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3219428"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/wevj15030099"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9838936"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05732-2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412616"},{"key":"ref36","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Deisenroth","year":"2011"},{"key":"ref37","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gu","year":"2016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3696-5"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref40","first-page":"49","article-title":"Logarithmic online regret bounds for undiscounted reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","author":"Auer","year":"2006"},{"key":"ref41","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"11","author":"Jaksch","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","first-page":"1763","article-title":"Online regret bounds for undiscounted continuous reinforcement learning","volume-title":"Proc. 25th Int. Conf. Neural Inf. Proces. Syst. (NIPS)","author":"Ortner","year":"2012"},{"key":"ref43","first-page":"3003","article-title":"(More) efficient reinforcement learning via posterior sampling","volume-title":"Proc. 26th Int. Conf. Neural Inf. Proces. Syst. (NIPS)","author":"Osband","year":"2013"},{"key":"ref44","first-page":"12123","article-title":"Bootstrapping upper confidence bound","volume-title":"Proc. 3rd Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Hao","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.23919\/ACC53348.2022.9867146"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref48","first-page":"81","article-title":"Variational regret bounds for reinforcement learning","volume-title":"Proc. 35th Uncertainty Artif. Intell. Conf.","author":"Ortner","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref50","first-page":"222","article-title":"Iterative linear quadratic regulator design for nonlinear biological movement systems","volume-title":"Proc. 1st Int. Conf. Inform. Control, Automat. Robot.","author":"Li","year":"2004"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-53859-8.00003-5"},{"key":"ref52","first-page":"529","article-title":"Multiple-step ahead prediction for non linear dynamic systemsa Gaussian process treatment with propagation of the uncertainty,","author":"Girard","year":"2002","journal-title":"Proc. Adv. Neural Inf. Proces. Syst. (NIPS)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9121-3"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2018.8503252"},{"key":"ref56","first-page":"341","article-title":"Recent advances in hierarchical reinforcement learning","volume-title":"Discrete Event Dyn. Syst.","volume":"13","author":"Barto","year":"2003"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500830"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11662-4_11"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref60","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Mach. Learn. Res.","author":"Haarnoja","year":"2018"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/25\/10747067\/10587084.pdf?arnumber=10587084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:31:30Z","timestamp":1732667490000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10587084\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":60,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2024.3424191","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"type":"print","value":"0018-9545"},{"type":"electronic","value":"1939-9359"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}