{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T17:39:42Z","timestamp":1769535582159,"version":"3.49.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2011,7,1]],"date-time":"2011-07-01T00:00:00Z","timestamp":1309478400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2011,7,1]],"date-time":"2011-07-01T00:00:00Z","timestamp":1309478400000},"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":[],"published-print":{"date-parts":[[2011,7]]},"DOI":"10.1109\/ijcnn.2011.6033520","type":"proceedings-article","created":{"date-parts":[[2011,10,6]],"date-time":"2011-10-06T13:24:17Z","timestamp":1317907457000},"page":"2333-2340","source":"Crossref","is-referenced-by-count":8,"title":["An online actor-critic learning approach with Levenberg-Marquardt algorithm"],"prefix":"10.1109","author":[{"given":"Zhen","family":"Ni","sequence":"first","affiliation":[{"name":"Department of Electrical, Computer and Biomedical Engineering, University of Rhode Island, Kingston, 02881, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibo","family":"He","sequence":"additional","affiliation":[{"name":"Department of Electrical, Computer and Biomedical Engineering, University of Rhode Island, Kingston, 02881, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danil V.","family":"Prokhorov","sequence":"additional","affiliation":[{"name":"Toyota Research Institute NA, TTC, Ann Arbor, MI 48105, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Automation, Wuhan University of Technology, Hubei 430070, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2004.843276"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"ref12","article-title":"Damping parameter in marquardt's method","author":"nielsen","year":"1999"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.03.012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368190"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544785"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref17","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2000396"},{"key":"ref4","article-title":"The Levenberg-Marquardt method of nonlinear least squares curve-fitting problems","author":"gavin","year":"2010"},{"key":"ref3","article-title":"The Levenberg-Marquardt Algorithm","author":"ranganathan","year":"2004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967373"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21111-9_1"},{"key":"ref8","article-title":"Methods for Non-Linear Least Squares Problems","author":"madsen","year":"2004"},{"key":"ref7","article-title":"Levenberg-Marquardt algorithm","author":"jlblanco","year":"2010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/72.914523"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref20","first-page":"2601","article-title":"Where Do Rewards Come From","author":"singh","year":"2009","journal-title":"Proc 8th Annu Conf Cognitive Sci Soc"},{"key":"ref22","article-title":"Intrinsically Motivated Reinforcement Learning","author":"singh","year":"2004","journal-title":"Prof Annual Conf Neural Information Processing Systems (NIPS'04)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1006\/ceps.1999.1020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICNSC.2010.5461483"},{"key":"ref23","article-title":"Intrinsically Motivated Learning of Hierarchical Collections of Skills","author":"barto","year":"2004","journal-title":"Proc Int?l Conf Development and Learning (ICDL 04)"},{"key":"ref26","article-title":"Reinforcement learning for on-line control and optimization","author":"govindhasamy","year":"2004","journal-title":"Intelligent Control Systems Using Computational Intelligence Techniques"},{"key":"ref25","article-title":"Adaptive Learning and Control for MIMO System Based On Adaptive Dynamic Programming","author":"fu","year":"2011","journal-title":"IEEE Trans Neural Netw"}],"event":{"name":"2011 International Joint Conference on Neural Networks (IJCNN 2011 - San Jose)","location":"San Jose, CA, USA","start":{"date-parts":[[2011,7,31]]},"end":{"date-parts":[[2011,8,5]]}},"container-title":["The 2011 International Joint Conference on Neural Networks"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6022827\/6033131\/06033520.pdf?arnumber=6033520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T05:01:40Z","timestamp":1769490100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6033520\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,7]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2011.6033520","relation":{},"subject":[],"published":{"date-parts":[[2011,7]]}}}