{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T18:08:12Z","timestamp":1778695692607,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation, the NSFC-Innovation and Development Joint Foundation of Chinese Automobile Industry","doi-asserted-by":"publisher","award":["1053717"],"award-info":[{"award-number":["1053717"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation, the NSFC-Innovation and Development Joint Foundation of Chinese Automobile Industry","doi-asserted-by":"publisher","award":["U1564214"],"award-info":[{"award-number":["U1564214"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51529701"],"award-info":[{"award-number":["51529701"]}],"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2017,4]]},"DOI":"10.1109\/tnnls.2015.2505084","type":"journal-article","created":{"date-parts":[[2016,1,27]],"date-time":"2016-01-27T19:09:02Z","timestamp":1453921742000},"page":"934-947","source":"Crossref","is-referenced-by-count":39,"title":["Manifold-Based Reinforcement Learning via Locally Linear Reconstruction"],"prefix":"10.1109","volume":"28","author":[{"given":"Xin","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibo","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.20"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2008.04.009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2014.2312322"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321780317"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1126\/science.295.5552.7a","article-title":"The isomap algorithm and topological stability","volume":"295","author":"balasubramanian","year":"2002","journal-title":"Science"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","article-title":"Nonlinear dimensionality reduction by locally linear embedding","volume":"290","author":"roweis","year":"2000","journal-title":"Science"},{"key":"ref37","first-page":"119","article-title":"Think globally, fit locally: Unsupervised learning of low dimensional manifolds","volume":"4","author":"saul","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref36","author":"wittman","year":"2005","journal-title":"MANIfold Learning MATLAB Demo"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2311578"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102421"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22887-2_4"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICNSC.2012.6204912"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252509"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref14","first-page":"2222","article-title":"Sketch-based linear value function approximation","volume":"25","author":"bellemare","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1109\/TNN.2011.2147797","article-title":"Adaptive learning and control for MIMO system based on adaptive dynamic programming","volume":"22","author":"fu","year":"2011","journal-title":"IEEE Trans Neural Netw"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref4","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref27","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.08.001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.07.008"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390251"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2236354"},{"key":"ref7","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":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01551-9","author":"szepesv\u00e1ri","year":"2010","journal-title":"Algorithms for Reinforcement Learning"},{"key":"ref9","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2168538"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_64"},{"key":"ref24","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511623783"},{"key":"ref23","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/37.341864"},{"key":"ref25","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"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/ielaam\/5962385\/7879455\/7393833-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/7879455\/07393833.pdf?arnumber=7393833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T16:52:12Z","timestamp":1692204732000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7393833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4]]},"references-count":43,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2015.2505084","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,4]]}}}