{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:04:12Z","timestamp":1774415052061,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ANIIFSE","award":["ANIIFSE_1_2019_1_159457"],"award-info":[{"award-number":["ANIIFSE_1_2019_1_159457"]}]},{"name":"NSF","award":["CAREER 1752362"],"award-info":[{"award-number":["CAREER 1752362"]}]},{"name":"NSF","award":["CPS 2136324"],"award-info":[{"award-number":["CPS 2136324"]}]},{"name":"NSF","award":["TRIPODS 1934979"],"award-info":[{"award-number":["TRIPODS 1934979"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/tac.2023.3240925","type":"journal-article","created":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T18:41:58Z","timestamp":1675190518000},"page":"2979-2994","source":"Crossref","is-referenced-by-count":6,"title":["Learning to Act Safely With Limited Exposure and Almost Sure Certainty"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3491-5746","authenticated-orcid":false,"given":"Agustin","family":"Castellano","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0600-3854","authenticated-orcid":false,"given":"Hancheng","family":"Min","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9950-1208","authenticated-orcid":false,"given":"Juan Andres","family":"Bazerque","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1568-1833","authenticated-orcid":false,"given":"Enrique","family":"Mallada","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9482829"},{"key":"ref2","first-page":"559","article-title":"Reinforcement learning with almost sure constraints","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Castellano","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00990"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4hws"},{"key":"ref7","volume-title":"Essentials of Robust Control","volume":"104","author":"Zhou","year":"1998"},{"key":"ref8","article-title":"Safe Model-based reinforcement learning with stability guarantees","volume":"30","author":"Berkenkamp","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref9","first-page":"803","article-title":"Lyapunov design for safe reinforcement learning","volume":"3","author":"Perkins","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ECC.2015.7330913"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5132"},{"issue":"1","key":"ref12","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garcia","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12103"},{"key":"ref15","first-page":"11480","article-title":"A primal approach to constrained policy optimization: Global optimality and finite-time analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2022.3152724"},{"key":"ref17","first-page":"3304","article-title":"Provably efficient safe exploration via primal-dual policy optimization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Ding","year":"2020"},{"key":"ref18","first-page":"9797","article-title":"Safe reinforcement learning in constrained Markov decision processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wachi","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16937"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref22","first-page":"9252","article-title":"Linear stochastic bandits under safety constraints","volume":"32","author":"Amani","year":"2019","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref23","first-page":"11191","article-title":"Stage-wise conservative linear bandits","volume":"33","author":"Moradipari","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/isit45174.2021.9518176"},{"key":"ref25","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","volume":"3","author":"Auer","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","first-page":"2827","article-title":"Stochastic bandits with linear constraints","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Pacchiano","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref28","first-page":"708","article-title":"Learning for safety-critical control with control barrier functions","volume-title":"Proc. Learn. Dyn. Control","author":"Taylor","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2003.7084971"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619646"},{"key":"ref31","volume-title":"Constrained Markov Decision Process","volume":"7","author":"Altman","year":"1998"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11662-4_12"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s001860050035"},{"key":"ref34","first-page":"8378","article-title":"Natural policy gradient primal-dual method for constrained Markov decision processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ding","year":"2020"},{"key":"ref35","article-title":"Stochastic primal-dual methods and sample complexity of reinforcement learning","author":"Chen","year":"2016"},{"key":"ref36","first-page":"3274","article-title":"Triple-q: A model-free algorithm for constrained reinforcement learning with sublinear regret and zero constraint violation","volume-title":"Proc. 25th Int. Conf. Artif. Intell. Statist.","author":"Wei","year":"2022"},{"key":"ref37","article-title":"Logically-constrained reinforcement learning","author":"Hasanbeig","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103949"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9028919"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS48487.2020.00017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177731118"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.spl.2017.11.017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3240925"},{"key":"ref45","volume-title":"Real Analysis: Modern Techniques and Their Applications","volume":"40","author":"Folland","year":"1999"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_72229"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2023.2451"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177731235"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9\/10109211\/10032771-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10109211\/10032771.pdf?arnumber=10032771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T17:06:28Z","timestamp":1709399188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10032771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":50,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tac.2023.3240925","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":[[2023,5]]}}}