{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T22:41:47Z","timestamp":1773528107287,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["62176259"],"award-info":[{"award-number":["62176259"]}],"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":["62373364"],"award-info":[{"award-number":["62373364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2022095"],"award-info":[{"award-number":["BE2022095"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcds.2024.3405896","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T17:57:54Z","timestamp":1717091874000},"page":"2070-2084","source":"Crossref","is-referenced-by-count":7,"title":["Deep Reinforcement Learning for Autonomous Driving Based on Safety Experience Replay"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7370-9289","authenticated-orcid":false,"given":"Xiaohan","family":"Huang","sequence":"first","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8454-0500","authenticated-orcid":false,"given":"Qiang","family":"Yu","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou Key Laboratory of Artificial Intelligence and Big Data, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3092715"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3231691"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3006621"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3117925"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2013.6579834"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2015.133"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2023.3323987"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3277288"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CCAA.2017.8229841"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"issue":"1","key":"ref12","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u00eda","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","article-title":"Sample efficient actor-critic with experience replay","author":"Wang","year":"2016"},{"key":"ref14","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Dosovitskiy","year":"2017"},{"issue":"1","key":"ref15","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref17","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/396"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294262"},{"key":"ref20","first-page":"32","article-title":"Reinforcement learning for autonomous maneuvering in highway scenarios","author":"Mirchevska","year":"2017","journal-title":"Workshop Driving Assistance Syst. Auton. Driving"},{"key":"ref21","article-title":"Deep constrained Q-learning","author":"Kalweit","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2021.3115980"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref24","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref25","first-page":"5048","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Andrychowicz","year":"2017"},{"key":"ref26","first-page":"1312","article-title":"Universal value function approximators","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schaul","year":"2015"},{"key":"ref27","article-title":"Replay for safety","author":"Szlak","year":"2021"},{"key":"ref28","first-page":"20","article-title":"Fast learning in an actor-critic architecture with reward and punishment","volume-title":"Proc. Scand. Conf. Artif. Intell.","author":"Balkenius","year":"2008"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2017.00010"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00039"},{"key":"ref31","first-page":"605","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver","year":"2014"},{"key":"ref32","first-page":"1","article-title":"Multi-critic actor learning: Teaching RL policies to act with style","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mysore","year":"2021"},{"key":"ref33","article-title":"Learning to be safe: Deep RL with a safety critic","author":"Srinivasan","year":"2020"},{"key":"ref34","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3013234"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.11"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10774064\/10542087.pdf?arnumber=10542087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T07:30:28Z","timestamp":1733297428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10542087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":38,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2024.3405896","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}