{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:38:48Z","timestamp":1755794328780,"version":"3.44.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2015,7,1]],"date-time":"2015-07-01T00:00:00Z","timestamp":1435708800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2015,7,1]],"date-time":"2015-07-01T00:00:00Z","timestamp":1435708800000},"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":[[2015,7]]},"DOI":"10.1109\/ijcnn.2015.7280311","type":"proceedings-article","created":{"date-parts":[[2015,10,1]],"date-time":"2015-10-01T17:48:02Z","timestamp":1443721682000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Approximate policy iteration with unsupervised feature learning based on manifold regularization"],"prefix":"10.1109","author":[{"given":"Hongliang","family":"Li","sequence":"first","affiliation":[{"name":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Derong","family":"Liu","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ding","family":"Wang","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2247418"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-1005-3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"ref14","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","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":"Journal of Machine Learning Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1561\/2200000003"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321780317"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2311578"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.07.008"},{"journal-title":"Reinforcement Learning and Approximate Dynamic Programming for Feedback Control","year":"2013","author":"lewis","key":"ref4"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01551-9","author":"szepesvari","year":"2010","journal-title":"Algorithms for Reinforcement Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2280013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2296206"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2357896"},{"journal-title":"Dynamic Programming","year":"1957","author":"bellman","key":"ref2"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.05.050"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"2319","DOI":"10.1126\/science.290.5500.2319","article-title":"A global geometric framework for nonlinear dimensionality reduction","volume":"290","author":"tenenbaum","year":"2000","journal-title":"Science"},{"key":"ref22","first-page":"1229","article-title":"Manifold regularization and semi-supervised learning: Some theoretical analyses","volume":"14","author":"niyogi","year":"2013","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","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":"Journal of Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2307349"},{"key":"ref23","first-page":"1","article-title":"Regularized least squares temporal difference learning with nested 12 and £1 penalization","author":"hoffman","year":"2011","journal-title":"Proceedings of the 9th European Workshop on Reinforcment Learning"}],"event":{"name":"2015 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2015,7,12]]},"location":"Killarney, Ireland","end":{"date-parts":[[2015,7,17]]}},"container-title":["2015 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7256526\/7280295\/07280311.pdf?arnumber=7280311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T18:14:11Z","timestamp":1755281651000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7280311\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2015.7280311","relation":{},"subject":[],"published":{"date-parts":[[2015,7]]}}}