{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T16:30:39Z","timestamp":1780072239359,"version":"3.54.0"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF China","award":["52221005"],"award-info":[{"award-number":["52221005"]}]},{"name":"NSF China","award":["U20A20334"],"award-info":[{"award-number":["U20A20334"]}]},{"name":"NSF China","award":["52072213"],"award-info":[{"award-number":["52072213"]}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004405","name":"Toyota Motor Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004405","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Didi"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tac.2023.3336263","type":"journal-article","created":{"date-parts":[[2023,11,23]],"date-time":"2023-11-23T19:21:08Z","timestamp":1700767268000},"page":"2713-2720","source":"Crossref","is-referenced-by-count":15,"title":["Synthesizing Control Barrier Functions With Feasible Region Iteration for Safe Reinforcement Learning"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7222-0019","authenticated-orcid":false,"given":"Yujie","family":"Yang","sequence":"first","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4272-5730","authenticated-orcid":false,"given":"Yuhang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5331-0938","authenticated-orcid":false,"given":"Wenjun","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0282-8621","authenticated-orcid":false,"given":"Jianyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2854-921X","authenticated-orcid":false,"given":"Yuming","family":"Yin","sequence":"additional","affiliation":[{"name":"College of Mechanical Engineering, Zhejiang University of Technology, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4923-3633","authenticated-orcid":false,"given":"Shengbo","family":"Eben Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303785"},{"key":"ref2","first-page":"97","article-title":"Joint synthesis of safety certificate and safe control policy using constrained reinforcement learning","volume-title":"Proc. 4th Annu. Learn. Dyn. Control Conf.","author":"Ma","year":"2022"},{"key":"ref3","article-title":"Model-based reinforcement learning for atari","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kaiser","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3163816"},{"issue":"1","key":"ref7","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garca","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8"},{"key":"ref10","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref11","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tessler","year":"2019"},{"key":"ref12","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"Ray","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3105491"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683520"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/ACC55779.2023.10156043"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341190"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8263977"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561561"},{"issue":"1","key":"ref23","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-8176-8086-2","volume-title":"Optimal Control","volume":"2","author":"Vinter","year":"2010"},{"key":"ref24","volume-title":"Constrained Optimal Control for Hybrid Systems","author":"Borrelli","year":"2003"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.073"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref27","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196132"},{"key":"ref29","first-page":"1110","article-title":"Learning to walk in the real world with minimal human effort","volume-title":"Proc. Conf. Robot Learn.","author":"Ha","year":"2021"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10485216\/10328440.pdf?arnumber=10328440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T15:12:09Z","timestamp":1711984329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10328440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":29,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tac.2023.3336263","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}