{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T16:34:34Z","timestamp":1780850074135,"version":"3.54.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation","doi-asserted-by":"publisher","award":["U19A2069"],"award-info":[{"award-number":["U19A2069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation","doi-asserted-by":"publisher","award":["U1664263"],"award-info":[{"award-number":["U1664263"]}],"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":["51975311"],"award-info":[{"award-number":["51975311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/tits.2021.3055899","type":"journal-article","created":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T19:52:30Z","timestamp":1657569150000},"page":"6357-6367","source":"Crossref","is-referenced-by-count":52,"title":["Learning to Drive Like Human Beings: A Method Based on Deep Reinforcement Learning"],"prefix":"10.1109","volume":"23","author":[{"given":"Yantao","family":"Tian","sequence":"first","affiliation":[{"name":"Department of Control Science and Engineering, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-6427","authenticated-orcid":false,"given":"Xuanhao","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Fei","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhu","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuewu","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2706978"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2604240"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2880409"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/25.845116"},{"key":"ref5","article-title":"Alvinn: An autonomous land vehicle in aneural network","author":"Pomerleau","year":"1989"},{"key":"ref6","article-title":"Off-roadobstacle avoidance through end-to-end learning","volume-title":"Advances in Neural Information Processing Systems","author":"LeCun","year":"2005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref8","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016","journal-title":"arXiv:1604.07316"},{"key":"ref9","article-title":"End-to-end learning of driving models from large-scale video datasets","author":"Xu","year":"2016","journal-title":"arXiv:1612.01079"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"issue":"39","key":"ref11","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref13","article-title":"QT-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"Kalashnikov","year":"2018","journal-title":"arXiv:1806.10293"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref15","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","author":"Espeholt","year":"2018","journal-title":"arXiv:1802.01561"},{"key":"ref16","article-title":"Relational deep reinforcement learning","author":"Zambaldi","year":"2018","journal-title":"arXiv:1806.01830"},{"key":"ref17","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"issue":"6","key":"ref18","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume":"8","author":"Lillicrap","year":"2015","journal-title":"Comput. Sci."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/FBIT.2007.37"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2019.2898964"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.11"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569635"},{"key":"ref24","article-title":"A deep reinforcement learning driving policy for autonomous road vehicles","author":"Makantasis","year":"2019","journal-title":"arXiv:1905.09046"},{"key":"ref25","article-title":"Target-driven visual navigation in indoor scenes using deep reinforcement learning","author":"Zhu","year":"2016","journal-title":"arXiv:1609.05143"},{"key":"ref26","article-title":"Learning to drive in a day","author":"Kendall","year":"2018","journal-title":"arXiv:1807.00412"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref28","article-title":"A brief survey of deep reinforcement learning","author":"Arulkumaran","year":"2017","journal-title":"arXiv:1708.05866"},{"key":"ref29","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv:1707.08817"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/EURCON.2007.4400335"},{"key":"ref31","article-title":"Reverse curriculum generation for reinforcement learning","author":"Florensa","year":"2017","journal-title":"arXiv:1707.05300"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"issue":"6","key":"ref34","first-page":"88","article-title":"Continuous control with deep reinforcement learning","volume":"8","author":"Lillicrap","year":"2016","journal-title":"Comput. Sci."},{"key":"ref35","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref36","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Mnih"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1103\/physrev.36.823"},{"key":"ref38","volume-title":"Introduction to Random Signals and Applied Kalman Filtering","author":"Brown","year":"1997"},{"key":"ref39","first-page":"13","article-title":"Reinforcement learning and the reward engineering principle","volume-title":"Proc. AAAI Spring Symp.","author":"Dewey"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref42","article-title":"Pretraining deep actor-critic reinforcement learning algorithms with expert demonstrations","author":"Zhang","year":"2018","journal-title":"arXiv:1801.10459"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-018-5697-1"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9826234\/09352233.pdf?arnumber=9352233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:16:36Z","timestamp":1704842196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9352233\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":43,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tits.2021.3055899","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}