{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:26:49Z","timestamp":1775744809767,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":["52225212"],"award-info":[{"award-number":["52225212"]}],"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":["52272418"],"award-info":[{"award-number":["52272418"]}],"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":["U22A20100"],"award-info":[{"award-number":["U22A20100"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB2503302"],"award-info":[{"award-number":["2022YFB2503302"]}],"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":[[2025,7]]},"DOI":"10.1109\/tits.2025.3543810","type":"journal-article","created":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T18:55:23Z","timestamp":1740682523000},"page":"10131-10145","source":"Crossref","is-referenced-by-count":7,"title":["A Preference-Based Multi-Agent Federated Reinforcement Learning Algorithm Framework for Trustworthy Interactive Urban Autonomous Driving"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5990-8633","authenticated-orcid":false,"given":"Sikai","family":"Lu","sequence":"first","affiliation":[{"name":"Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0633-9887","authenticated-orcid":false,"given":"Yingfeng","family":"Cai","sequence":"additional","affiliation":[{"name":"Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0801-236X","authenticated-orcid":false,"given":"Ze","family":"Liu","sequence":"additional","affiliation":[{"name":"Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, China"}]},{"given":"Yubo","family":"Lian","sequence":"additional","affiliation":[{"name":"BYD Auto Industry Company Ltd., Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2079-3867","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9136-8091","authenticated-orcid":false,"given":"Hai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automotive and Traffic Engineering and the Engineering Technology Research Institute, Jiangsu University, Zhenjiang, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01178"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00718"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2020.3046646"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3059674"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01494"},{"key":"ref6","article-title":"The role of coverage in online reinforcement learning","author":"Xie","year":"2022","journal-title":"arXiv:2210.04157"},{"key":"ref7","article-title":"Harnessing density ratios for online reinforcement learning","author":"Amortila","year":"2024","journal-title":"arXiv:2401.09681"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tnsm.2021.3120804"},{"key":"ref9","first-page":"9460","article-title":"Defining and characterizing reward gaming","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"35","author":"Skalse"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.4271\/10-07-03-0018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103568"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ictai59109.2023.00115"},{"key":"ref13","article-title":"A survey of reinforcement learning from human feedback","author":"Kaufmann","year":"2023","journal-title":"arXiv:2312.14925"},{"key":"ref14","article-title":"WebGPT: Browser-assisted question-answering with human feedback","author":"Nakano","year":"2021","journal-title":"arXiv:2112.09332"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ccdc62350.2024.10587696"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref17","article-title":"Federated deep reinforcement learning","author":"Hankui Zhuo","year":"2019","journal-title":"arXiv:1901.08277"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2022.3219644"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/dyspan53946.2021.9677132"},{"key":"ref20","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","author":"Fu","year":"2017","journal-title":"arXiv:1710.11248"},{"key":"ref21","first-page":"66","article-title":"Learning by cheating","volume-title":"Proc. Conf. Rob. Learn.","author":"Chen"},{"key":"ref22","first-page":"6152","article-title":"PEBBLE: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Lee"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10341795"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3233231"},{"key":"ref26","article-title":"A survey of explainable reinforcement learning","author":"Milani","year":"2022","journal-title":"arXiv:2202.08434"},{"key":"ref27","first-page":"5979","article-title":"Discovering symbolic policies with deep reinforcement learning","volume-title":"Proc. Mach. Learn. Res., Online","volume":"139","author":"Landajuela"},{"key":"ref28","article-title":"Contrastive explanations for reinforcement learning via embedded self predictions","author":"Lin","year":"2020","journal-title":"arXiv:2010.05180"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16935"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipl.2005.11.003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413535"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3227717"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00532"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.376"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20259"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3427551"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01530"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3370836"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11063346\/10907775.pdf?arnumber=10907775","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T17:30:46Z","timestamp":1751563846000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10907775\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":40,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3543810","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}