{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T19:47:11Z","timestamp":1770752831873,"version":"3.50.0"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,3]]},"DOI":"10.1109\/adprl.2009.4927523","type":"proceedings-article","created":{"date-parts":[[2009,5,19]],"date-time":"2009-05-19T19:50:44Z","timestamp":1242762644000},"page":"36-41","source":"Crossref","is-referenced-by-count":35,"title":["Online policy iteration based algorithms to solve the continuous-time infinite horizon optimal control problem"],"prefix":"10.1109","author":[{"given":"Kyriakos","family":"Vamvoudakis","sequence":"first","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Draguna","family":"Vrabie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Frank","family":"Lewis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]}],"member":"263","reference":[{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1989.70114"},{"key":"15","author":"werbos","year":"1974","journal-title":"Beyond regression New tools for prediction and analysis in the behavior sciences"},{"key":"16","article-title":"approximate dynamic programming for real-time control and neural modeling","author":"werbos","year":"1992","journal-title":"Handbook of Intelligent Control"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2008.4738955"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"12","author":"sutton","year":"1998","journal-title":"Reinforcement Learning - An Introduction"},{"key":"3","doi-asserted-by":"crossref","first-page":"2159","DOI":"10.1016\/S0005-1098(97)00128-3","article-title":"galerkin approximations of the generalized hamilton-jacobi-bellman equation","volume":"33","author":"beard","year":"1997","journal-title":"Automatica"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374604"},{"key":"1","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1016\/j.automatica.2004.11.034","article-title":"nearly optimal control laws for nonlinear systems with saturating actuators using a neural network hjb approach","volume":"41","author":"abu-khalaf","year":"2005","journal-title":"Automatica"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.801727"},{"key":"7","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2006.889499"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"4","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098829"},{"key":"8","author":"lewis","year":"1995","journal-title":"Optimal Control"}],"event":{"name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","location":"Nashville, TN, USA","start":{"date-parts":[[2009,3,30]]},"end":{"date-parts":[[2009,4,2]]}},"container-title":["2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4910084\/4927513\/04927523.pdf?arnumber=4927523","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,18]],"date-time":"2017-06-18T20:02:34Z","timestamp":1497816154000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4927523\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,3]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/adprl.2009.4927523","relation":{},"subject":[],"published":{"date-parts":[[2009,3]]}}}