{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T18:01:16Z","timestamp":1767981676598,"version":"3.49.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2015,2,1]],"date-time":"2015-02-01T00:00:00Z","timestamp":1422748800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61273136"],"award-info":[{"award-number":["61273136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61034002"],"award-info":[{"award-number":["61034002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing","doi-asserted-by":"crossref","award":["4122083"],"award-info":[{"award-number":["4122083"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2015,2]]},"DOI":"10.1109\/tnnls.2014.2371046","type":"journal-article","created":{"date-parts":[[2014,12,2]],"date-time":"2014-12-02T20:37:22Z","timestamp":1417552642000},"page":"346-356","source":"Crossref","is-referenced-by-count":71,"title":["MEC\u2014A Near-Optimal Online Reinforcement Learning Algorithm for Continuous Deterministic Systems"],"prefix":"10.1109","volume":"26","author":[{"family":"Dongbin Zhao","sequence":"first","affiliation":[]},{"family":"Yuanheng Zhu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15880-3_44"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5202-y"},{"key":"ref33","first-page":"306","article-title":"Exploration in metric state spaces","author":"kakade","year":"2003","journal-title":"Proc 20th Int Conf Mach Learn (ICML)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143955"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102459"},{"key":"ref30","first-page":"213","article-title":"R-max—A general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73580-9_21"},{"key":"ref36","article-title":"PAC optimal exploration in continuous space Markov decision processes","author":"pazis","year":"2013","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5186-7"},{"key":"ref34","first-page":"1209","article-title":"Multi-resolution exploration in continuous spaces","volume":"21","author":"nouri","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-4757-2","author":"zhang","year":"2013","journal-title":"Adaptive Dynamic Programming for Control Algorithms and Stability"},{"key":"ref40","first-page":"733","article-title":"Online exploration in least-squares policy iteration","volume":"2","author":"li","year":"2009","journal-title":"Proc 8th Int Conf Auto Agents Multiagent Syst (AAMAS)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2203336"},{"key":"ref12","article-title":"The role of exploration in learning control","author":"thrun","year":"1992","journal-title":"Handbook for Intelligent Control Neural Fuzzy and Adaptive Approaches"},{"key":"ref13","author":"thrun","year":"1992"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2013.2295351"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2300532"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2357896"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1109\/TNNLS.2013.2280013","article-title":"Decentralized stabilization for a class of continuous-time nonlinear interconnected systems using online learning optimal control approach","volume":"25","author":"liu","year":"2014","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2236354"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2270561"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920269"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1109\/TNNLS.2013.2281663","article-title":"Policy iteration adaptive dynamic programming algorithm for discrete-time nonlinear systems","volume":"25","author":"liu","year":"2014","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref27","first-page":"3471","article-title":"The application of ADHDP( $\\lambda $ ) method to coordinated multiple ramps metering","volume":"5","author":"bai","year":"2009","journal-title":"Int J Innovative Comput"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.06.037"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.04.006"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2012.0486"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.027"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.23919\/ACC.1989.4790360","article-title":"neural network control of unknown nonlinear systems","author":"li","year":"1989","journal-title":"1989 American Control Conference ACC"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.049"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1109\/TNNLS.2013.2280013","article-title":"Decentralized stabilization for a class of continuous-time nonlinear interconnected systems using online learning optimal control approach","volume":"25","author":"liu","year":"2014","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"988","DOI":"10.1109\/TSMCB.2008.922019","article-title":"Adaptive critic learning techniques for engine torque and air–fuel ratio control","volume":"38","author":"liu","year":"2008","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2013.0472"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2011.0783"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-013-1110-y"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1109\/TSMCB.2012.2216523","article-title":"Finite-approximation-error-based optimal control approach for discrete-time nonlinear systems","volume":"43","author":"liu","year":"2013","journal-title":"IEEE Trans Cybern"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.09.034"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2122257"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6706755"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.05.032"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/7010866\/06971146.pdf?arnumber=6971146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:04:59Z","timestamp":1642003499000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6971146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,2]]},"references-count":43,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2014.2371046","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,2]]}}}