{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T11:15:13Z","timestamp":1766056513068,"version":"3.48.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100002465","name":"Delta","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002465","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018915","name":"Shanghai Automotive Industry Science and Technology Development Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018915","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247462","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"15268-15275","source":"Crossref","is-referenced-by-count":0,"title":["Continuously Improved Reinforcement Learning for Automated Driving"],"prefix":"10.1109","author":[{"given":"Xuerun","family":"Yan","sequence":"first","affiliation":[{"name":"Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhexi","family":"Lian","sequence":"additional","affiliation":[{"name":"Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Hu","sequence":"additional","affiliation":[{"name":"Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongwei","family":"Feng","sequence":"additional","affiliation":[{"name":"Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binyang","family":"Song","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongji University,Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Shanghai,China,201804"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trd.2023.103607"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2016.09.010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3307873"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2024.3402126"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104654"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2022.03.013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914621"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104683"},{"issue":"97","key":"ref10","first-page":"1","article-title":"Safe policy iteration: A monotonically improving approximate policy iteration approach","volume":"22","author":"Metelli","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00610-y"},{"key":"ref12","first-page":"2380","article-title":"High confidence policy improvement","volume-title":"International Conference on Machine Learning","author":"Thomas"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3144867"},{"key":"ref14","first-page":"9797","article-title":"Safe reinforcement learning in constrained markov decision processes","volume-title":"International Conference on Machine Learning","author":"Wachi"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3069497"},{"article-title":"Efficient learning of safe driving policy via human-ai copilot optimization","year":"2022","author":"Li","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104632"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3271642"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285440"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3332655"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref23","article-title":"Actor-critic algorithms","volume":"12","author":"Konda","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/wics.56"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2019.02215"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3388161"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32460-4_11"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref31","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto"},{"key":"ref32","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247462.pdf?arnumber=11247462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T11:10:52Z","timestamp":1766056252000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247462\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247462","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}