{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T02:28:21Z","timestamp":1777084101208,"version":"3.51.4"},"reference-count":62,"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":"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":"Cyber Valley Initiative"},{"name":"International Max Planck Research School for Intelligent Systems"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/tac.2022.3200948","type":"journal-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T17:48:51Z","timestamp":1669744131000},"page":"2743-2757","source":"Crossref","is-referenced-by-count":8,"title":["Safe Value Functions"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8019-4401","authenticated-orcid":false,"given":"Pierre-Fran\u00e7ois","family":"Massiani","sequence":"first","affiliation":[{"name":"Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4916-7464","authenticated-orcid":false,"given":"Steve","family":"Heim","sequence":"additional","affiliation":[{"name":"Biomimetic Robotics Lab, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2623-5652","authenticated-orcid":false,"given":"Friedrich","family":"Solowjow","sequence":"additional","affiliation":[{"name":"Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2785-2487","authenticated-orcid":false,"given":"Sebastian","family":"Trimpe","sequence":"additional","affiliation":[{"name":"Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref57","article-title":"Regions of Attraction for Hybrid Limit Cycles of Walking Robots","author":"manchester","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8263977"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.032"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912452673"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039601"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2982584"},{"key":"ref53","article-title":"Reward constrained policy optimization","author":"tessler","year":"0","journal-title":"Int Conf Learn Representations"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2616644"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7140083"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46024-6"},{"key":"ref54","volume":"1","author":"bertsekas","year":"2005","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-104941"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683085"},{"key":"ref19","article-title":"Learning stability certificates from data","author":"boffi","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561561"},{"key":"ref51","article-title":"Constrained reinforcement learning has zero duality gap","author":"paternain","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1137\/19M1305835"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2910739"},{"key":"ref45","author":"fleming","year":"2006","journal-title":"Controlled Markov Processes and Viscosity Solutions"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1976.10480949"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4755-1"},{"key":"ref42","first-page":"620","article-title":"Constrained upper confidence reinforcement learning","volume":"120","author":"zheng","year":"0","journal-title":"Proc 2nd Conf Learn Dyn Control"},{"key":"ref41","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes Stochastic Modeling"},{"key":"ref44","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref43","first-page":"1451","article-title":"Safe exploration in Markov decision processes","author":"moldovan","year":"0","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.077"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2975727"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341606"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2014.08.002"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16684-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.100"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914528132"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1017\/9781108980647"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.011"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461237"},{"key":"ref37","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"ray","year":"0"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids43949.2019.9035003"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562093"},{"key":"ref33","article-title":"Learning event-triggered control from data through joint optimization","year":"0","journal-title":"IFAC J Syst Control"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196924"},{"key":"ref2","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc\u00eda","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683088"},{"key":"ref38","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","first-page":"905","article-title":"On exploration requirements for learning safety constraints","author":"massiani","year":"0","journal-title":"Learning for Dynamics and Control"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794107"},{"key":"ref26","article-title":"Reinforcement learning with bounded risk","author":"geibel","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","first-page":"2891","article-title":"Safe exploration for interactive machine learning","author":"turchetta","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303785"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211035177"},{"key":"ref21","first-page":"627","article-title":"A learnable safety measure","author":"heim","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3152724"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057055"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2782818"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s004220000162"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2018.03.008"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10109211\/09865237.pdf?arnumber=9865237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T15:07:35Z","timestamp":1684163255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9865237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":62,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tac.2022.3200948","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]]}}}