{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T04:15:03Z","timestamp":1745554503703,"version":"3.40.4"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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","award":["2022YFB2502901"],"award-info":[{"award-number":["2022YFB2502901"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF China","award":["U20A20334","52072213"],"award-info":[{"award-number":["U20A20334","52072213"]}]},{"DOI":"10.13039\/501100019339","name":"Tsinghua University Initiative Scientific Research Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019339","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tcyb.2025.3542223","type":"journal-article","created":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T17:40:01Z","timestamp":1742319601000},"page":"2327-2340","source":"Crossref","is-referenced-by-count":0,"title":["Feasible Policy Iteration With Guaranteed Safe Exploration"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4272-5730","authenticated-orcid":false,"given":"Yuhang","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7222-0019","authenticated-orcid":false,"given":"Yujie","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4923-3633","authenticated-orcid":false,"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1539-472X","authenticated-orcid":false,"given":"Yao","family":"Lyu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3697-1576","authenticated-orcid":false,"given":"Jingliang","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"given":"Zhilong","family":"Zheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Green Vehicle and Mobility, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"given":"Dezhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Idriverplus Technology Company Ltd., Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2024.3364428"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2982201"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2381604"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2967995"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3238656"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2014-6048"},{"key":"ref14","first-page":"97","article-title":"Joint synthesis of safety certificate and safe control policy using constrained reinforcement learning","volume-title":"Proc. 4th Annu. Conf. Learn. Dyn. Control (L4DC)","author":"Ma"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3348422"},{"issue":"1","key":"ref16","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":"ref17","first-page":"25636","article-title":"Reachability constrained reinforcement learning","volume-title":"Proc. 39th Int. Conf. Mach. Learn. (ICML)","author":"Yu"},{"key":"ref18","article-title":"Feasible policy iteration","author":"Yang","year":"2024","journal-title":"arXiv:2304.08845"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3163816"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3152724"},{"key":"ref21","first-page":"9133","article-title":"Responsive safety in reinforcement learning by PID lagrangian methods","volume-title":"Proc. 37th Int. Conf. Mach. Learn. (ICML)","author":"Stooke"},{"key":"ref22","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57957-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2654539"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref26","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018","journal-title":"arXiv:1801.08757"},{"key":"ref27","first-page":"1","article-title":"Safe exploration in reinforcement learning: A generalized formulation and algorithms","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","volume":"36","author":"Wachi"},{"key":"ref28","first-page":"25621","article-title":"Learning barrier certificates: Towards safe reinforcement learning with zero training-time violations","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Luo"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120261"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3225203"},{"key":"ref31","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3537087"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2023.100096"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2021.3058064"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221036\/10974960\/10931147.pdf?arnumber=10931147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T05:18:40Z","timestamp":1745471920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10931147\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":35,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2025.3542223","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"type":"print","value":"2168-2267"},{"type":"electronic","value":"2168-2275"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}