{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T10:51:57Z","timestamp":1782125517462,"version":"3.54.5"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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. Intell. Transport. Syst."],"published-print":{"date-parts":[[2020,1]]},"DOI":"10.1109\/tits.2019.2942014","type":"journal-article","created":{"date-parts":[[2019,9,25]],"date-time":"2019-09-25T20:05:43Z","timestamp":1569441943000},"page":"433-443","source":"Crossref","is-referenced-by-count":271,"title":["Development of an Efficient Driving Strategy for Connected and Automated Vehicles at Signalized Intersections: A Reinforcement Learning Approach"],"prefix":"10.1109","volume":"21","author":[{"given":"Mofan","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6751-5293","authenticated-orcid":false,"given":"Yang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0973-3756","authenticated-orcid":false,"given":"Xiaobo","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"4481","article-title":"Maximizing the probability of arriving on time: A practical Q-learning method","author":"cao","year":"2017","journal-title":"Proc AAAI"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460567"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2014.2307551"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2013.11.024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2005.11.001"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2006.01.057"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2613997"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2016.01.001"},{"key":"ref35","first-page":"3814","article-title":"Multiagent-based route guidance for increasing the chance of arrival on time","author":"cao","year":"2016","journal-title":"Proc AAAI"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2006.884615"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WAC.2006.376059"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/0001-4575(94)90042-6"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-947X(2002)128:2(182)"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s40534-016-0117-3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2015.1016023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3141\/1999-01"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3141\/2324-08"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2006.11.002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2014.09.014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2016.05.007"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2011.11.003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ITST.2006.288906"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3141\/2423-03"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.04.015"},{"key":"ref25","article-title":"Synthesis of active traffic management experiences in Europe and the United States","author":"fuhs","year":"2010"},{"key":"ref50","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"1999","journal-title":"Proc NIPS"},{"key":"ref51","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proc NIPS"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2017.07.003"},{"key":"ref58","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017","journal-title":"arXiv 1707 02286"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref56","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"arXiv 1512 03385"},{"key":"ref55","author":"tieleman","year":"2012","journal-title":"Neural networks for machine learning lecture 6a overview of mini-batch gradient descent"},{"key":"ref54","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"arXiv 1706 02275"},{"key":"ref53","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":"ref52","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2012.09.011"},{"key":"ref40","article-title":"An efficient deep reinforcement learning model for urban traffic control","author":"lin","year":"2018","journal-title":"arXiv 1808 01876"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2157145"},{"key":"ref13","article-title":"Microscopic car-following model for autonomous vehicles using reinforcement learning","author":"zhou","year":"0"},{"key":"ref14","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref15","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2012.01.009"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/10\/3\/033001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.physleta.2015.05.019"},{"key":"ref4","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2010.2076320"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2014.09.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2278494"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2016.06.010"},{"key":"ref49","author":"williams","year":"1988","journal-title":"Toward a theory of reinforcement-learning connectionist systems"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref45","first-page":"398","article-title":"Emergent behaviors in mixed-autonomy traffic","author":"wu","year":"2017","journal-title":"Proc Conf Robot Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref42","article-title":"Modeling uncertainty in vehicle trajectory prediction in a mixed connected and autonomous vehicle environment using deep learning and kernel density estimation","author":"li","year":"2018","journal-title":"Proc 4th Annu Symp Transp Inform"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2017.1387546"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2725912"},{"key":"ref43","article-title":"Deep learning-based human-driven vehicle trajectory prediction and its application for platoon control of connected and autonomous vehicles","volume":"2018","author":"lin","year":"0"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/8946909\/08848852.pdf?arnumber=8848852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T16:00:26Z","timestamp":1651075226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8848852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1]]},"references-count":63,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tits.2019.2942014","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1]]}}}