{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:25:42Z","timestamp":1773246342309,"version":"3.50.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["52272331"],"award-info":[{"award-number":["52272331"]}],"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":["52232012"],"award-info":[{"award-number":["52232012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Australian Research Council (ARC) Discovery Early Career Researcher Award (DECRA) Fellowship","award":["DE220100265"],"award-info":[{"award-number":["DE220100265"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tits.2024.3368474","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T20:21:15Z","timestamp":1710793275000},"page":"7751-7766","source":"Crossref","is-referenced-by-count":13,"title":["Enhancing Car-Following Performance in Traffic Oscillations Using Expert Demonstration Reinforcement Learning"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6944-0053","authenticated-orcid":false,"given":"Meng","family":"Li","sequence":"first","affiliation":[{"name":"School of Transportation, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7192-6853","authenticated-orcid":false,"given":"Zhibin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Transportation, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3656-0328","authenticated-orcid":false,"given":"Zehong","family":"Cao","sequence":"additional","affiliation":[{"name":"STEM, University of South Australia, Adelaide, SA, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2012.01.009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102934"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3153472"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.102987"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3152550"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2019.07.001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2010.0084"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2017.04.025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2019.05.014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103801"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.07.011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103421"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1049\/itr2.12494"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/4419907"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103452"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024655"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103656"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0361198120937976"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2019.2947756"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2942014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071959"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12803"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2021.3100709"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103744"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref26","article-title":"Simplifying deep reinforcement learning via self-supervision","author":"Zha","year":"2021","journal-title":"arXiv:2106.05526"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3177685"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tcst.2010.2049203"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2019.105345"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103729"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3221450"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3270356"},{"key":"ref35","article-title":"Human-in-the-loop deep reinforcement learning with application to autonomous driving","author":"Wu","year":"2021","journal-title":"arXiv:2104.07246"},{"key":"ref36","article-title":"Efficient learning of safe driving policy via human-AI copilot optimization","author":"Li","year":"2022","journal-title":"arXiv:2202.10341"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref38","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv:1707.08817"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103987"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.064"},{"key":"ref41","first-page":"1652","article-title":"Don\u2019t start from scratch: Leveraging prior data to automate robotic reinforcement learning","volume-title":"Proc. The 6th Conf. Robot Learn.","author":"Walke"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102662"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12825"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2019.05.017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2021.106051"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"issue":"1","key":"ref47","first-page":"103","article-title":"Reinforcement learning: An introduction","volume":"21","author":"Thrun","year":"2000","journal-title":"AI Mag."},{"key":"ref48","article-title":"#Exploration: A study of count-based exploration for deep reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","author":"Tang","year":"2017"},{"key":"ref49","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Advances in Neural Information Processing Systems","author":"Bellemare","year":"2016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2007.12.004"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2942050"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2016.08.007"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1061\/jtepbs.0000584"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103047"},{"key":"ref55","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2022.127520"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104019"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10582787\/10475137.pdf?arnumber=10475137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:42:16Z","timestamp":1733884936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10475137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":57,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tits.2024.3368474","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}