{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T16:07:22Z","timestamp":1787069242007,"version":"build-2736575974"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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":["61871283"],"award-info":[{"award-number":["61871283"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation of Pre-Research on Equipment of China","award":["61400010304"],"award-info":[{"award-number":["61400010304"]}]},{"name":"Major Civil-Military Integration Project in Tianjin, China","award":["18ZXJMTG00170"],"award-info":[{"award-number":["18ZXJMTG00170"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tcds.2021.3092715","type":"journal-article","created":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T17:40:05Z","timestamp":1624902005000},"page":"2041-2052","source":"Crossref","is-referenced-by-count":47,"title":["A Deep Reinforcement Learning Algorithm Suitable for Autonomous Vehicles: Double Bootstrapped Soft-Actor\u2013Critic-Discrete"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2558-552X","authenticated-orcid":false,"given":"Jiachen","family":"Yang","sequence":"first","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9638-2741","authenticated-orcid":false,"given":"Jipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8207-3921","authenticated-orcid":false,"given":"Meng","family":"Xi","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3513-3201","authenticated-orcid":false,"given":"Yutian","family":"Lei","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiwen","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6245"},{"key":"ref2","volume-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97909-0_46"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2018.09.011"},{"key":"ref5","volume-title":"An improved hybrid CTC-attention model for speech recognition","author":"Yuan","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706675"},{"key":"ref7","volume-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00657"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref10","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref11","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","volume-title":"Advances in Neural Information Processing Systems","author":"Sutton","year":"1996"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3133169"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref15","volume-title":"End-to-end deep reinforcement learning for lane keeping assist","author":"Sallab","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.4271\/07-11-01-0003"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500645"},{"key":"ref18","volume-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"ref19","volume-title":"Soft actor-critic for discrete action settings","author":"Christodoulou","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2410258"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979587"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995949"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995935"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995936"},{"key":"ref25","volume-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref27","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref28","volume-title":"Deep reinforcement learning with weighted Q-learning","author":"Cini","year":"2020"},{"key":"ref29","volume-title":"Concrete dropout","author":"Gal","year":"2017"},{"key":"ref30","volume-title":"Is Q-learning provably efficient?","author":"Jin","year":"2018"},{"key":"ref31","volume-title":"Deep reinforcement learning and the deadly triad","author":"Van Hasselt","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref33","volume-title":"Distributed distributional deterministic policy gradients","author":"Barth-Maron","year":"2018"},{"key":"ref34","volume-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"ref35","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref36","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6156"},{"key":"ref38","volume-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2538961"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2843122"},{"key":"ref42","volume-title":"Maximum a Posteriori policy optimisation","author":"Abdolmaleki","year":"2018"},{"key":"ref43","volume-title":"Discovering reinforcement learning algorithms","author":"Oh","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500675"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2904417"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2942014"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317839"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3034800"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref51","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Osband","year":"2016"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/444"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2628817"},{"key":"ref54","volume-title":"Boosting soft actor-critic: Emphasizing recent experience without forgetting the past","author":"Wang","year":"2019"},{"key":"ref55","volume-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref56","volume-title":"An Environment for Autonomous Driving Decision-Making","author":"Leurent","year":"2018"},{"key":"ref57","volume-title":"OpenAI gym","author":"Brockman","year":"2016"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10360134\/09466157.pdf?arnumber=9466157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T17:20:13Z","timestamp":1704993613000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9466157\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":57,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2021.3092715","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}