{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T23:57:30Z","timestamp":1782863850063,"version":"3.54.5"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2015,5,1]],"date-time":"2015-05-01T00:00:00Z","timestamp":1430438400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Institute of BioMed-IT, Energy-IT and Smart-IT Technology (BEST), a Brain Korea 21 plus program at Yonsei University"},{"name":"Basic Science Research Program through the National Research Foundation of Korea(NRF)"},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","award":["No. NRF-2013R1A1A2012609"],"award-info":[{"award-number":["No. NRF-2013R1A1A2012609"]}],"id":[{"id":"10.13039\/501100002701","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":[[2015,5]]},"DOI":"10.1109\/tnnls.2014.2328590","type":"journal-article","created":{"date-parts":[[2014,8,22]],"date-time":"2014-08-22T15:47:45Z","timestamp":1408722465000},"page":"916-932","source":"Crossref","is-referenced-by-count":93,"title":["Integral Reinforcement Learning for Continuous-Time Input-Affine Nonlinear Systems With Simultaneous Invariant Explorations"],"prefix":"10.1109","volume":"26","author":[{"family":"Jae Young Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Jin Bae Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Yoon Ho Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","author":"ioannou","year":"1995","journal-title":"Stable and Robust Adaptive Control"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2050211"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1986.267469"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/oca.986"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098829"},{"key":"ref35","article-title":"Constrained nonlinear optimal control: A converse HJB approach","author":"nevisti?","year":"1996"},{"key":"ref34","author":"khalil","year":"2002","journal-title":"Nonlinear Systems"},{"key":"ref10","article-title":"Invariantly admissible policy iteration for a class of nonlinear optimal control problems","author":"lee","year":"2014","journal-title":"Syst Control Lett"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.801727"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.03.008"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"2850","DOI":"10.1016\/j.automatica.2012.06.008","article-title":"Integral Q-learning and explorized policy iteration for adaptive optimal control of continuous-time linear systems","volume":"48","author":"lee","year":"2012","journal-title":"Automatica"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252508"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"2699","DOI":"10.1016\/j.automatica.2012.06.096","article-title":"Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics","volume":"48","author":"jiang","year":"2012","journal-title":"Automatica"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.12.009"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.09.019"},{"key":"ref19","first-page":"493","article-title":"Approximate dynamic programming for real-time control and neural modeling","author":"werbos","year":"1992","journal-title":"Handbook of Intelligent Control Neural Fuzzy and Adaptive Approaches"},{"key":"ref28","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"ref27","author":"kirk","year":"2004","journal-title":"Optimal Control Theory An Introduction"},{"key":"ref3","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"J Artif Intell Res"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2200501"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"2159","DOI":"10.1016\/S0005-1098(97)00128-3","article-title":"Galerkin approximation of the generalized Hamilton–Jacobi equation","volume":"33","author":"beard","year":"1996","journal-title":"Automatica"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1979.4310171"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544785"},{"key":"ref9","article-title":"Improving the closed-loop performance of nonlinear systems","author":"beard","year":"1995"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref21","article-title":"Online adaptive optimal control for continuous-time systems","author":"vrabie","year":"2010"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.automatica.2012.09.019","article-title":"A novel actor–critic–identifier architecture for approximate optimal control of uncertain nonlinear systems","volume":"49","author":"bhasin","year":"2013","journal-title":"Automatica"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3018"},{"key":"ref26","author":"lewis","year":"1995","journal-title":"Optimal Control"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2276571"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/5962385\/7086401\/06882245.pdf?arnumber=6882245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:41:50Z","timestamp":1641987710000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/ieeexplore.ieee.org\/document\/6882245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5]]},"references-count":36,"journal-issue":{"issue":"5"},"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/tnnls.2014.2328590","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,5]]}}}