{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T17:00:46Z","timestamp":1791478846090,"version":"4.3.4"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CCF-1763896"],"award-info":[{"award-number":["CCF-1763896"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CPS-1851588"],"award-info":[{"award-number":["CPS-1851588"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["S&AS-1849198"],"award-info":[{"award-number":["S&AS-1849198"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1109\/tnnls.2020.2978805","type":"journal-article","created":{"date-parts":[[2020,3,19]],"date-time":"2020-03-19T21:32:46Z","timestamp":1584653566000},"page":"405-419","source":"Crossref","is-referenced-by-count":22,"title":["Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9637-854X","authenticated-orcid":false,"given":"Ankush","family":"Chakrabarty","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Devesh K.","family":"Jha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9777-3090","authenticated-orcid":false,"given":"Gregery T.","family":"Buzzard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7209-7866","authenticated-orcid":false,"given":"Yebin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1978-4848","authenticated-orcid":false,"given":"Kyriakos G.","family":"Vamvoudakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/MCS.2016.2621461","article-title":"Game theory-based control system algorithms with real-time reinforcement learning: How to solve multiplayer games online","volume":"37","author":"vamvoudakis","year":"2017","journal-title":"IEEE Control Syst Mag"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MCS.2012.2214134","article-title":"Reinforcement learning and feedback control: Using natural decision methods to design optimal adaptive controllers","volume":"32","author":"lewis","year":"2012","journal-title":"IEEE Control Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2017.08.1050"},{"key":"ref32","article-title":"Conservative decision-making and inference in uncertain dynamical systems","author":"calliess","year":"2014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2898835"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2539222"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF00939912"},{"key":"ref36","first-page":"549","article-title":"On the convergence of an algorithm for finding a global extremum","volume":"11","author":"strongin","year":"1973","journal-title":"Eng Cybern"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF00229304"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431484"},{"key":"ref28","author":"khalil","year":"2015","journal-title":"Nonlinear Control"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/81.721270"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2681520"},{"key":"ref2","volume":"1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2015.7172127"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2382338"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2017.2702118"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.09.032"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3182\/20140824-6-ZA-1003.01896"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.06.010"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1268","DOI":"10.1016\/j.automatica.2007.09.016","article-title":"$\\mathcal{H}_\\infty$\n filtering for uncertain stochastic time-delay systems with sector-bounded nonlinearities","volume":"44","author":"wang","year":"2008","journal-title":"Automatica"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2027233"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2276571"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"1884","DOI":"10.1109\/TNNLS.2012.2217349","article-title":"Neural network based online simultaneous policy update algorithm for solving the hji equation in nonlinear $\\mathcal{H}_\\infty$\n control","volume":"23","author":"wu","year":"2012","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(90)90021-9"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2702566"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2016.12.003"},{"key":"ref55","first-page":"3598","article-title":"Q-learning and Pontryagin’s minimum principle","author":"mehta","year":"2009","journal-title":"Proc IEEE Conf Decis Control (CDC)"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2487972"},{"key":"ref10","first-page":"2380","article-title":"High confidence policy improvement","author":"thomas","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7526565"},{"key":"ref40","first-page":"211","article-title":"Sparse Bayesian learning and the relevance vector machine","volume":"1","author":"tipping","year":"2001","journal-title":"J Mach Learn Res"},{"key":"ref12","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref13","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","first-page":"8092","article-title":"A Lyapunov-based approach to safe reinforcement learning","author":"chow","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798708"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794229"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2949757"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref3","author":"vrabie","year":"2013","journal-title":"Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2712188"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/INES.2015.7329650"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2897814"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1002\/oca.2313"},{"key":"ref9","first-page":"213","article-title":"R-max—A general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970777"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2166384"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.11.034"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/9.317135"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963430"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102369"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1030741073"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/9312808\/9042816-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9312808\/09042816.pdf?arnumber=9042816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:01Z","timestamp":1652194381000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9042816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":59,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2978805","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}