{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:23:03Z","timestamp":1777501383197,"version":"3.51.4"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004364","name":"BP","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004364","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,17]]},"DOI":"10.1109\/case58245.2025.11163999","type":"proceedings-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:24:07Z","timestamp":1758648247000},"page":"2450-2455","source":"Crossref","is-referenced-by-count":2,"title":["Safety-Guaranteed Policy Composition via Generalized Policy Improvement for Autonomous Vehicles"],"prefix":"10.1109","author":[{"given":"Ni","family":"Mu","sequence":"first","affiliation":[{"name":"Tsinghua University,Center for Intelligent and Networked System (CFINS), Beijing Key Laboratory of Embodied Intelligence Systems,Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Luan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Center for Intelligent and Networked System (CFINS), Beijing Key Laboratory of Embodied Intelligence Systems,Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing-Shan","family":"Jia","sequence":"additional","affiliation":[{"name":"Tsinghua University,Center for Intelligent and Networked System (CFINS), Beijing Key Laboratory of Embodied Intelligence Systems,Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00520-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1057\/s41599-025-04554-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103656"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-27026-9"},{"key":"ref5","article-title":"Summary report: Standing general order on crash reporting for level 2 advanced driver assistance systems","year":"2022"},{"key":"ref6","article-title":"The dangers of driverless cars","author":"Law","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.17083\/ijsg.v10i4.638"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3268500"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s42154-023-00231-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2955905"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CAC59555.2023.10450959"},{"key":"ref13","article-title":"Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CASE59546.2024.10711622"},{"key":"ref15","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3623377"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1991.4791982"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0952-1976(02)00070-2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref23","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref25","article-title":"E-mapp: Efficient multi-agent reinforcement learning with parallel program guidance","author":"Chang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CAC63892.2024.10865310"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CAC59555.2023.10450595"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/664"},{"key":"ref29","article-title":"Clarify: Contrastive preference reinforcement learning for untangling ambiguous queries","volume-title":"Proceedings of the 42th International Conference on Machine Learning","author":"Mu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3559241"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3236579"},{"key":"ref33","article-title":"Successor features for transfer in reinforcement learning","volume":"30","author":"Barreto","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89722-4_12"},{"key":"ref35","article-title":"An environment for autonomous driving decision-making","author":"Leurent","year":"2018"}],"event":{"name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","location":"Los Angeles, CA, USA","start":{"date-parts":[[2025,8,17]]},"end":{"date-parts":[[2025,8,21]]}},"container-title":["2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11163731\/11163732\/11163999.pdf?arnumber=11163999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:15:31Z","timestamp":1759295731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11163999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,17]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/case58245.2025.11163999","relation":{},"subject":[],"published":{"date-parts":[[2025,8,17]]}}}