{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:54:12Z","timestamp":1783184052111,"version":"3.54.6"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3045114","type":"journal-article","created":{"date-parts":[[2020,12,17]],"date-time":"2020-12-17T02:36:17Z","timestamp":1608172577000},"page":"229086-229100","source":"Crossref","is-referenced-by-count":68,"title":["Stability-Certified Reinforcement Learning: A Control-Theoretic Perspective"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7909-4545","authenticated-orcid":false,"given":"Ming","family":"Jin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javad","family":"Lavaei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"11423","article-title":"Efficient and accurate estimation of Lipschitz constants for deep neural networks","author":"fazlyab","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"3183","DOI":"10.1016\/S1474-6670(17)56543-X","article-title":"An IQC-based stability criterion for systems with slowly varying parameters","volume":"32","author":"helmersson","year":"1999","journal-title":"IFAC Proc Volumes"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970777"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2005.1582282"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2000.877001"},{"key":"ref37","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","author":"kakade","year":"2002","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","first-page":"5767","article-title":"Improved training of wasserstein gans","author":"gulrajani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00928"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/72.165600"},{"key":"ref10","article-title":"A berkeley view of systems challenges for AI","author":"stoica","year":"2017","journal-title":"arXiv 1712 05855"},{"key":"ref11","first-page":"803","article-title":"Lyapunov design for safe reinforcement learning","volume":"3","author":"perkins","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(92)90029-F"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ECC.2016.7810344"},{"key":"ref13","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"berkenkamp","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039601"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref16","first-page":"1803","article-title":"How to explain individual classification decisions","volume":"11","author":"baehrens","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref17","first-page":"1","article-title":"Improving the adversarial robustness and interpretability of deep neural networks by regularizing their input gradients","author":"ross","year":"2018","journal-title":"Proc AAAI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/9.587335"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3731"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971309"},{"key":"ref3","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.11.029"},{"key":"ref6","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref5","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/0306007"},{"key":"ref8","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref7","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"2002","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","article-title":"Concrete problems in AI safety","author":"amodei","year":"2016","journal-title":"arXiv 1606 06565"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref20","volume":"36","author":"dullerud","year":"2013","journal-title":"A Course in Robust Control Theory A Convex Approach"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2008.03.004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8618996"},{"key":"ref42","first-page":"183","article-title":"Multi-agent reinforcement learning: An overview","author":"bu?oniu","year":"2010","journal-title":"Innovations in Multi-Agent Systems and Applications - 1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref23","volume":"40","author":"zhou","year":"1996","journal-title":"Robust and Optimal Control"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2562062"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2829473"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2361004"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/15M1009597"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1134\/S000511790611004X"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/8948470\/9296215-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09296215.pdf?arnumber=9296215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:53:37Z","timestamp":1649444017000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9296215\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3045114","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}