{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:32:46Z","timestamp":1781973166371,"version":"3.54.5"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"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":["61233001"],"award-info":[{"award-number":["61233001"]}],"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":["61273140"],"award-info":[{"award-number":["61273140"]}],"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":["61304086"],"award-info":[{"award-number":["61304086"]}],"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":["61533017"],"award-info":[{"award-number":["61533017"]}],"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":["61503377"],"award-info":[{"award-number":["61503377"]}],"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":["U1501251"],"award-info":[{"award-number":["U1501251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4162065"],"award-info":[{"award-number":["4162065"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Early Career Development Award of SKLMCCS"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/tnnls.2017.2650943","type":"journal-article","created":{"date-parts":[[2017,1,27]],"date-time":"2017-01-27T19:58:35Z","timestamp":1485547115000},"page":"932-943","source":"Crossref","is-referenced-by-count":27,"title":["Manifold Regularized Reinforcement Learning"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5387-0825","authenticated-orcid":false,"given":"Hongliang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3715-4778","authenticated-orcid":false,"given":"Derong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7149-5712","authenticated-orcid":false,"given":"Ding","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273545"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273585"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321780317"},{"key":"ref32","first-page":"721","article-title":"LSTD with random projections","author":"ghavamzadeh","year":"2010","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref31","article-title":"Sparse approximate policy evaluation using graph-based basis functions","author":"johns","year":"2009"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2236354"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1561\/2200000003"},{"key":"ref36","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":"ref35","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2319"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553442"},{"key":"ref27","first-page":"441","article-title":"Regularized policy iteration","author":"farahmand","year":"2008","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.11.021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"ref24","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1023\/A:1022192903948","article-title":"Least squares policy evaluation algorithms with linear function approximation","volume":"13","author":"nedi?","year":"2003","journal-title":"Discrete Event Dyn Syst"},{"key":"ref26","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5038-2"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280311"},{"key":"ref51","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref58","first-page":"2","article-title":"Deep belief nets as function approximators for reinforcement learning","author":"abtahi","year":"2011","journal-title":"Proc 15th AAAI Conf Lifelong Learn"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2014.7010626"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.006"},{"key":"ref55","first-page":"3041","article-title":"Finite-sample analysis of least-squares policy iteration","volume":"13","author":"lazaric","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref54","first-page":"615","article-title":"Finite-sample analysis of LSTD","author":"lazaric","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref53","first-page":"560","article-title":"Error bounds for approximate policy iteration","author":"munos","year":"2003","journal-title":"Proc 20th Int Conf Mach Learn"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2307349"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2011.0783"},{"key":"ref40","first-page":"1","article-title":"Towards feature selection in actor-critic algorithms","author":"rohanimanesh","year":"2009","journal-title":"Proc Workshop Abstraction Reinforcement Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2402203"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2357896"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2296206"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.05.050"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2354377"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2280974"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2012.0486"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2013.2295351"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01551-9","author":"szepesvari","year":"2010","journal-title":"Algorithms for Reinforcement Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-015-0893-y"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref8","author":"lewis","year":"2013","journal-title":"Reinforcement Learning and Approximate Dynamic Programming for Feedback Control"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"key":"ref49","first-page":"1149","article-title":"Laplacian support vector machines trained in the primal","volume":"12","author":"melacci","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927540"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0710743106"},{"key":"ref48","first-page":"1229","article-title":"Manifold regularization and semi-supervised learning: Some theoretical analyses","volume":"14","author":"niyogi","year":"2013","journal-title":"J Mach Learn Res"},{"key":"ref47","first-page":"2399","article-title":"Manifold regularization: A geometric framework for learning from labeled and unlabeled examples","volume":"7","author":"belkin","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-008-9095-6"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2311578"},{"key":"ref44","first-page":"1369","article-title":"Linearly-solvable Markov decision problems","author":"todorov","year":"2006","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.07.008"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8318959\/07835715.pdf?arnumber=7835715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T22:50:01Z","timestamp":1658530201000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7835715\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":59,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2017.2650943","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,4]]}}}