{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T20:04:59Z","timestamp":1760299499394,"version":"3.41.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/cdc.2016.7798966","type":"proceedings-article","created":{"date-parts":[[2017,1,5]],"date-time":"2017-01-05T17:11:18Z","timestamp":1483636278000},"page":"4578-4585","source":"Crossref","is-referenced-by-count":7,"title":["Learning to control partial differential equations: Regularized Fitted Q-Iteration approach"],"prefix":"10.1109","author":[{"given":"Amir-massoud","family":"Farahmand","sequence":"first","affiliation":[]},{"given":"Saleh","family":"Nabi","sequence":"additional","affiliation":[]},{"given":"Piyush","family":"Grover","sequence":"additional","affiliation":[]},{"given":"Daniel N.","family":"Nikovski","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"1349","article-title":"Value pursuit iteration","author":"farahmand","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NIPS - 25)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/jfm.2014.182"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2009.52"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1007\/b97848","author":"gy\u00f6rfi","year":"2002","journal-title":"A Distribution-Free Theory of Nonparametric Regression"},{"journal-title":"The Elements of Statistical Learning Data Mining Inference and Prediction","year":"2001","author":"hastie","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/040614384"},{"key":"ref17","first-page":"815","article-title":"Finite-time bounds for fitted value iteration","volume":"9","author":"munos","year":"2008","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref18","first-page":"317","article-title":"Neural fitted Q iteration - first experiences with a data efficient neural reinforcement learning method","author":"riedmiller","year":"2005","journal-title":"16th European Conference on Machine Learning"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1007\/3-540-44581-1_27","article-title":"A generalized representer theorem","author":"sch\u00f6lkopf","year":"2001","journal-title":"Proc Annu Conf Computational Learning Theory (COLT)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6759923"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2016.01.011"},{"journal-title":"Regularization in Reinforcement Learning","year":"2011","author":"farahmand","key":"ref6"},{"key":"ref5","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref8","first-page":"1","article-title":"Regularized policy iteration with nonparametric function spaces","volume":"17","author":"farahmand","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2009.5160611"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2009.5160552"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2011.5991540"},{"key":"ref9","first-page":"568","article-title":"Error propagation for approximate policy and value iteration","author":"farahmand","year":"2010","journal-title":"Advances in Neural Information Processing Systems (NIPS - 23)"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-77242-4","author":"steinwart","year":"2008","journal-title":"Support Vector Machines"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01551-9","author":"szepesv\u00e1ri","year":"2010","journal-title":"Algorithms for Reinforcement Learning"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref21"},{"journal-title":"All of Nonparametric Statistics","year":"2007","author":"wasserman","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1088\/0951-7715\/25\/2\/R1"}],"event":{"name":"2016 IEEE 55th Conference on Decision and Control (CDC)","start":{"date-parts":[[2016,12,12]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2016,12,14]]}},"container-title":["2016 IEEE 55th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7786694\/7798233\/07798966.pdf?arnumber=7798966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T01:22:31Z","timestamp":1749864151000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7798966\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cdc.2016.7798966","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}