{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T07:29:22Z","timestamp":1768548562606,"version":"3.49.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tnnls.2022.3142501","type":"journal-article","created":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T22:12:02Z","timestamp":1643667122000},"page":"7365-7376","source":"Crossref","is-referenced-by-count":8,"title":["Data-Driven Policy Iteration for Nonlinear Optimal Control Problems"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2528-3935","authenticated-orcid":false,"given":"Corrado","family":"Possieri","sequence":"first","affiliation":[{"name":"Istituto di Analisi dei Sistemi ed Informatica A. Ruberti, Consiglio Nazionale delle Ricerche, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4525-4656","authenticated-orcid":false,"given":"Mario","family":"Sassano","sequence":"additional","affiliation":[{"name":"Dipartimento di Ingegneria Civile e Ingegneria Informatica, University of Rome ‘Tor Vergata,”, Rome, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.2979389"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2684458"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927523"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2955438"},{"key":"ref11","author":"vrabie","year":"2013","journal-title":"Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2016.12.003"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2010.5531586"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2905715"},{"key":"ref18","article-title":"Q-learning for optimal control of continuous-time systems","author":"luo","year":"2014","journal-title":"arXiv 1410 2954"},{"key":"ref46","article-title":"Constrained nonlinear optimal control: A converse HJB approach","author":"nevisti?","year":"1996"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.09.019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2296206"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MCS.2012.2214134","article-title":"Reinforcement learning and feedback control","volume":"32","author":"lewis","year":"2012","journal-title":"IEEE Control Syst Mag"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1986.1104168"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(96)00060-3"},{"key":"ref44","author":"adams","year":"2003","journal-title":"Sobolev Spaces"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/9.210149"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.04.027"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2009.5164743"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.096"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g0s"},{"key":"ref3","author":"kwakernaak","year":"1972","journal-title":"Linear Optimal Control Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-8086-2"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/72.363477"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCS.1978.1084534"},{"key":"ref34","article-title":"Identification and control of nonlinear systems using neural network models: Design and stability analysis","author":"polycarpou","year":"1991"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2006.377430"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098829"},{"key":"ref31","author":"rudin","year":"1976","journal-title":"Principles of Mathematical Analysis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2009.2017116"},{"key":"ref33","author":"ioannou","year":"2012","journal-title":"Robust Adaptive Control"},{"key":"ref32","author":"sastry","year":"2011","journal-title":"Adaptive Control Stability Convergence and Robustness"},{"key":"ref2","author":"athans","year":"1966","journal-title":"Optimal Control"},{"key":"ref1","first-page":"102","article-title":"Contributions to the theory of optimal control","volume":"5","author":"kalman","year":"1960","journal-title":"Boletín Sociedad Matemática"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/5.119551"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2050211"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374604"},{"key":"ref23","author":"berkovitz","year":"2019","journal-title":"Nonl Optimal Control Theory"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.801727"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(97)00128-3"},{"key":"ref20","first-page":"739","article-title":"Hamilton-Jacobi-Bellman equations for Q-learning in continuous time","author":"kim","year":"2020","journal-title":"Proc 2nd Conf Learn Dyn Control"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g0s"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441712"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2006.889499"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.11.034"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2008.4738955"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10273172\/09697330.pdf?arnumber=9697330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:16:59Z","timestamp":1698085019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9697330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":49,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3142501","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}