{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T20:30:44Z","timestamp":1780086644701,"version":"3.54.0"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"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":["61922026"],"award-info":[{"award-number":["61922026"]}],"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":["62033003"],"award-info":[{"award-number":["62033003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Province Higher Vocational Colleges and Schools Pearl River Scholar approved in 2018"},{"name":"Guangdong Natural Science Funds for Distinguished Young Scholar","award":["2018B030306013"],"award-info":[{"award-number":["2018B030306013"]}]},{"name":"Local Innovative and Research Teams Project of Guangdong Special Support Program","award":["2019BT02X353"],"award-info":[{"award-number":["2019BT02X353"]}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","award":["2017B010116006"],"award-info":[{"award-number":["2017B010116006"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Basic and Applied Basic Research Foundation of Guangdong Province of China","award":["2019A1515111075"],"award-info":[{"award-number":["2019A1515111075"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/tnnls.2021.3116063","type":"journal-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T22:46:52Z","timestamp":1634770012000},"page":"3680-3690","source":"Crossref","is-referenced-by-count":73,"title":["Deep Reinforcement Learning on Autonomous Driving Policy With Auxiliary Critic Network"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9509-2670","authenticated-orcid":false,"given":"Yuanqing","family":"Wu","sequence":"first","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siqin","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Dongguan University of Technology, Dongguan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Renquan","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref12","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"Comput Sci"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref14","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref11","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"Comput Sci"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2011.5940562"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2293499"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317839"},{"key":"ref16","first-page":"305","article-title":"ALVINN: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref18","article-title":"Simulated car racing championship: Competition software manual","author":"loiacono","year":"2013","journal-title":"Comput Sci"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref23","article-title":"Exploration by random network distillation","author":"burda","year":"2018","journal-title":"arXiv 1810 12894"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref25","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"arXiv 1802 09477"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500645"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref21","article-title":"Torcs the open racing car simulator","author":"wymann","year":"2013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2020.1003417"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.2987963"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3109-x"},{"key":"ref3","article-title":"Reinforcement learning control of a flexible two-link manipulator: An experimental investigation","author":"he","year":"2020","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10175014\/09582785.pdf?arnumber=9582785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T17:33:39Z","timestamp":1690824819000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9582785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":26,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3116063","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}