{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T20:31:55Z","timestamp":1767990715648,"version":"3.49.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2014,12,1]],"date-time":"2014-12-01T00:00:00Z","timestamp":1417392000000},"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":["61075072"],"award-info":[{"award-number":["61075072"]}],"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":["91220301"],"award-info":[{"award-number":["91220301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"New Century Excellent Talent Plan","award":["NCET-10-0901"],"award-info":[{"award-number":["NCET-10-0901"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/tcyb.2014.2311578","type":"journal-article","created":{"date-parts":[[2014,4,25]],"date-time":"2014-04-25T18:02:00Z","timestamp":1398448920000},"page":"2613-2625","source":"Crossref","is-referenced-by-count":31,"title":["A Clustering-Based Graph Laplacian Framework for Value Function Approximation in Reinforcement Learning"],"prefix":"10.1109","volume":"44","author":[{"family":"Xin Xu","sequence":"first","affiliation":[]},{"family":"Zhenhua Huang","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Graves","sequence":"additional","affiliation":[]},{"given":"Witold","family":"Pedrycz","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0810600105"},{"key":"ref38","first-page":"2153","article-title":"On the Nyström method for approximating a gram matrix for improved kernel-based learning","volume":"6","author":"drineas","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref33","first-page":"1491","article-title":"Batch value function approximation via support vectors","author":"dietterich","year":"2001","journal-title":"Proc NIPS"},{"key":"ref32","first-page":"154","article-title":"Bayes meets Bellman: The Gaussian process approach to temporal difference learning","author":"engel","year":"2003","journal-title":"Proc ICML"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref37","article-title":"Spectral graph theory","author":"chung","year":"1997","journal-title":"Number 92 in CBMS Regional Conference Series in Mathematics"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511623783"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2236354"},{"key":"ref34","first-page":"751","article-title":"Gaussian processes in reinforcement learning","author":"rasmussen","year":"2003","journal-title":"Proc NIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2148710"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9939-1969-0255573-1"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1863","DOI":"10.1109\/TNN.2011.2168422","article-title":"Hierarchical approximate policy iteration with binary-tree state space decomposition","volume":"22","author":"xu","year":"2011","journal-title":"IEEE Trans Neural Netw"},{"key":"ref12","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2170565"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref15","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 Part B Cybern"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2168538"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1997.641481"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1592","DOI":"10.23919\/ACC.2004.1386804","article-title":"Optimal control synthesis of a class of nonlinear systems using single network adaptive critics","volume":"2","author":"padhi","year":"2004","journal-title":"Proceedings of the 2004 American Control Conference ACC"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368167"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2027233"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0098-3004(84)90020-7"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920231"},{"key":"ref29","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363573"},{"key":"ref7","first-page":"319","article-title":"Infinite-horizon policy-gradient estimation","volume":"12","author":"bartlett","year":"2001","journal-title":"J Artif Intell Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"ref20","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","volume":"8","author":"sutton","year":"1996","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref22","first-page":"2169","article-title":"Proto-value functions: A Laplacian framework for learning representation and control in Markov decision processes","volume":"8","author":"mahadevan","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102421"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/9780470140529"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/9780470061190"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.12.019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2010.2040479"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/6936410\/06805593.pdf?arnumber=6805593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:00:35Z","timestamp":1642003235000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6805593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":40,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2014.2311578","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,12]]}}}