{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:26:27Z","timestamp":1777490787386,"version":"3.51.4"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"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":["71871057"],"award-info":[{"award-number":["71871057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2242019R40060"],"award-info":[{"award-number":["2242019R40060"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2242020K40056"],"award-info":[{"award-number":["2242020K40056"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2242020K40063"],"award-info":[{"award-number":["2242020K40063"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council Discovery Early Career Researcher Award (ARC DECRA) Fellowship","doi-asserted-by":"publisher","award":["DE220100265"],"award-info":[{"award-number":["DE220100265"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1109\/tnnls.2021.3071959","type":"journal-article","created":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T01:02:58Z","timestamp":1619053378000},"page":"5309-5322","source":"Crossref","is-referenced-by-count":137,"title":["A Reinforcement Learning-Based Vehicle Platoon Control Strategy for Reducing Energy Consumption in Traffic Oscillations"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6944-0053","authenticated-orcid":false,"given":"Meng","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3656-0328","authenticated-orcid":false,"given":"Zehong","family":"Cao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7192-6853","authenticated-orcid":false,"given":"Zhibin","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.12.015"},{"key":"ref38","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017","journal-title":"arXiv 1707 02286"},{"key":"ref33","article-title":"Learning nearly decomposable value functions via communication minimization","author":"wang","year":"2019","journal-title":"arXiv 1910 05366"},{"key":"ref32","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","author":"das","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","article-title":"Cooperative multi-agent control using deep reinforcement learning","author":"gupta","year":"2017","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029187"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2016.2594588"},{"key":"ref35","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2942014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref29","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019","journal-title":"arXiv 1905 05408"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.05.025"},{"key":"ref1","article-title":"A European strategy for low-emission mobility","year":"2016","journal-title":"Communication from the Commission to the European Parliament the Council the European Economic and Social Committee and the Committee of the Regions"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.trd.2018.07.014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2015.11.001"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/0361198120937976"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102662"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500630"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.10.024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2007.12.004"},{"key":"ref51","article-title":"Integrated adaptive cruise control car-following model based on trajectory data","author":"su","year":"2016"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2931583"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC.2017.7978560"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2019.08.002"},{"key":"ref55","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2012.2198478"},{"key":"ref53","first-page":"1422","article-title":"On the impact of cooperative autonomous vehicles in improving freeway merging: A modified intelligent driver model-based approach","volume":"18","author":"zhou","year":"2017","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2014.09.001"},{"key":"ref10","article-title":"A review of cooperative multi-agent deep reinforcement learning","author":"oroojlooyjadid","year":"2019","journal-title":"arXiv 1908 03963"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2019.05.017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref13","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"Proc AAMAS"},{"key":"ref14","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"1","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref16","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"arXiv 1803 11485"},{"key":"ref17","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play StarCraft combat games","author":"peng","year":"2017","journal-title":"arXiv 1703 10069"},{"key":"ref19","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","author":"singh","year":"2018","journal-title":"arXiv 1812 09755"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2019.07.001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.04.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2013.11.023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2019.06.005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.114030"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927531"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2018.03.009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2013.2241460"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2010.133"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2018.2806996"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2809917"},{"key":"ref42","first-page":"110","article-title":"Traffic studies at T-junctions. 4. The effect of speed on gap acceptance and conflict rate","volume":"18","author":"cooper","year":"1977","journal-title":"Traffic Eng Control"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2019.105345"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2465174"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2345734"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9629429\/09410239.pdf?arnumber=9410239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:14Z","timestamp":1652194394000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9410239\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":58,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3071959","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12]]}}}