{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:46:36Z","timestamp":1784249196242,"version":"3.55.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61903034"],"award-info":[{"award-number":["61903034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1913203"],"award-info":[{"award-number":["U1913203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973034"],"award-info":[{"award-number":["61973034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018621","name":"Program for Changjiang Scholars and Innovative Research Team in University","doi-asserted-by":"publisher","award":["IRT-16R06"],"award-info":[{"award-number":["IRT-16R06"]}],"id":[{"id":"10.13039\/501100018621","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018621","name":"Program for Changjiang Scholars and Innovative Research Team in University","doi-asserted-by":"publisher","award":["T2014224"],"award-info":[{"award-number":["T2014224"]}],"id":[{"id":"10.13039\/501100018621","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012236","name":"Beijing Institute of Technology Research Fund Program for Young Scholars","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012236","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tvt.2023.3275582","type":"journal-article","created":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T17:39:55Z","timestamp":1683913195000},"page":"12615-12627","source":"Crossref","is-referenced-by-count":27,"title":["Multi-Agent Reinforcement Learning-Based Decision Making for Twin-Vehicles Cooperative Driving in Stochastic Dynamic Highway Environments"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4140-9729","authenticated-orcid":false,"given":"Siyuan","family":"Chen","sequence":"first","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3618-7423","authenticated-orcid":false,"given":"Meiling","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4121-908X","authenticated-orcid":false,"given":"Wenjie","family":"Song","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3964-2433","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyin","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574716000229"},{"key":"ref35","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922266"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref15","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"lowe","year":"0","journal-title":"Proc 31st Int Conf Adv Neural Inf Process Syst"},{"key":"ref37","article-title":"CVXOPT: Convex optimization","author":"andersen","year":"2021"},{"key":"ref14","first-page":"225","article-title":"Traffic management strategies for multi-robotic rigid payload transport systems","author":"sirineni","year":"0","journal-title":"Proc IEEE Int Symp Multi-Robot Multi-Agent Syst"},{"key":"ref36","article-title":"Bidirectional LSTM-CRF models for sequence tagging","author":"huang","year":"2015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref30","article-title":"RIIT: Rethinking the importance of implementation tricks in multi-agent reinforcement learning","author":"hu","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3047129"},{"key":"ref33","first-page":"3326","article-title":"Inequity aversion improves cooperation in intertemporal social dilemmas","volume":"31","author":"hughes","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref10","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2007.09.019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294679"},{"key":"ref1","article-title":"Baidu apollo em motion planner","author":"fan","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISIC.2014.6967622"},{"key":"ref39","author":"rajamani","year":"2011","journal-title":"Vehicle Dynamics and Control"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2013.05.004"},{"key":"ref38","first-page":"987","article-title":"Optimal trajectory generation for dynamic street scenarios in a frenet frame","author":"werling","year":"0","journal-title":"Proc IEEE Int Conf Robot Automat"},{"key":"ref19","first-page":"1043","article-title":"Formation control using GQ($\\lambda$) reinforcement learning","author":"knopp","year":"0","journal-title":"Proc IEEE Int Symp Robot Human Interact Commun"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/70.736776"},{"key":"ref24","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6859177"},{"key":"ref26","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"0","journal-title":"Proc 17th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref25","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref20","article-title":"Multi-robot formation control using reinforcement learning","author":"rawat","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225196"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34387-2_49"},{"key":"ref28","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"rashid","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref27","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","author":"wang","year":"0","journal-title":"Proc 9th Int Conf Learn Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3012034"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460934"},{"key":"ref3","article-title":"Deep reinforcement learning for autonomous driving","author":"wang","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3041278"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3165251"},{"key":"ref40","article-title":"An environment for autonomous driving decision-making","author":"leurent","year":"2018"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/10287112\/10123696.pdf?arnumber=10123696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T19:22:57Z","timestamp":1699298577000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10123696\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":40,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2023.3275582","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}