{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:52:52Z","timestamp":1777459972433,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2013,12,1]],"date-time":"2013-12-01T00:00:00Z","timestamp":1385856000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1109\/tnnls.2013.2270561","type":"journal-article","created":{"date-parts":[[2013,11,1]],"date-time":"2013-11-01T18:02:05Z","timestamp":1383328925000},"page":"1944-1956","source":"Crossref","is-referenced-by-count":26,"title":["Online Selective Kernel-Based Temporal Difference Learning"],"prefix":"10.1109","volume":"24","author":[{"family":"Xingguo Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Yang Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Ruili Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1609","article-title":"A convergent <formula formulatype=\"inline\"><tex Notation=\"TeX\">${O}(n)$<\/tex><\/formula> algorithm for off-policy temporal-difference learning with linear function approximation","volume":"21","author":"sutton","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"356","article-title":"Incremental least-squares temporal difference learning","author":"geramifard","year":"2006","journal-title":"Proc 21st AAAI Conf Artif Intell"},{"key":"ref33","first-page":"2643","article-title":"Bounded kernel-based online learning","volume":"10","author":"orabona","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390247"},{"key":"ref31","first-page":"1","article-title":"Sparse kernel-<formula formulatype=\"inline\"><tex Notation=\"TeX\">${\\rm SARSA}\\,(\\lambda)$<\/tex><\/formula> with an eligibility trace","author":"robards","year":"2011","journal-title":"Proc 13th Eur Conf Mach Learn"},{"key":"ref30","first-page":"1719","article-title":"A non-parametric approach to dynamic programming","volume":"23","author":"kroemer","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"ref35","author":"bradtke","year":"1994","journal-title":"Incremental Dynamic Programming for On-Line Adaptive Optimal Control"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1950","DOI":"10.1109\/TNET.2012.2187923","article-title":"An information theoretic approach of designing sparse kernel adaptive filters","volume":"20","author":"liu","year":"2009","journal-title":"IEEE Trans Neural Netw"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2009.5160344"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5038-2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553504"},{"key":"ref2","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","first-page":"154","article-title":"Bayes meets Bellman: The Gaussian process approach to temporal difference learning","author":"engel","year":"2003","journal-title":"Proc 20th Int Conf Mach Learn"},{"key":"ref22","first-page":"428","article-title":"Kernel rewards regression: An information efficient batch policy iteration approach","author":"schneega\ufffd","year":"2006","journal-title":"Proc IASTED Int Conf Arti Intell Appl"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102377"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/11881070_8"},{"key":"ref23","first-page":"1","article-title":"Kernel-based models for reinforcement learning","author":"jong","year":"2006","journal-title":"ICML Workshop on Kernel Machines and Reinforcement Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390259"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2008.4587201"},{"key":"ref50","first-page":"833","article-title":"Reinforcement learning in continuous action spaces through sequential Monte Carlo methods","volume":"20","author":"bonarini","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-010-0581-3"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1137\/10080484X"},{"key":"ref52","first-page":"174","article-title":"Methods for computing state similarity in Markov decision processes","author":"ferns","year":"2006","journal-title":"Proc 11th Conf Uncertainty Artificial Intell"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1270","DOI":"10.1109\/TNN.2010.2050334","article-title":"Approximate robust policy iteration using multilayer perceptron neural networks for discounted infinite-horizon Markov decision processes with uncertain correlated transition matrices","volume":"21","author":"li","year":"2010","journal-title":"IEEE Trans Neural Netw"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2076370"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2210559"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2227339"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref16","first-page":"227","article-title":"Multi kernel learning with online-batch optimization","volume":"13","author":"orabona","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2201261"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1007\/3-540-44581-1_27","article-title":"A generalized representer theorem","author":"sch\ufffdlkopf","year":"2001","journal-title":"Proc 14th Comput Learn Theory"},{"key":"ref19","first-page":"312","article-title":"Adaptive bases for reinforcement learning","author":"castro","year":"2010","journal-title":"Proc Eur Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/72.935097"},{"key":"ref6","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"key":"ref8","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368199"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390251"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.900227"},{"key":"ref46","author":"lappalainen","year":"2000","journal-title":"Advances in Independent Component Analysis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/34.58871"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2005.849817"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00190-X"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2007.896668"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017467"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2022007"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1155\/2008\/784292"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/6651762\/06570737.pdf?arnumber=6570737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,29]],"date-time":"2021-11-29T20:50:39Z","timestamp":1638219039000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6570737\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12]]},"references-count":53,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2013.2270561","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,12]]}}}