{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T12:08:04Z","timestamp":1764936484995},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540897217"},{"type":"electronic","value":"9783540897224"}],"license":[{"start":{"date-parts":[[2008,1,1]],"date-time":"2008-01-01T00:00:00Z","timestamp":1199145600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008]]},"DOI":"10.1007\/978-3-540-89722-4_20","type":"book-chapter","created":{"date-parts":[[2008,11,26]],"date-time":"2008-11-26T08:57:14Z","timestamp":1227689834000},"page":"253-267","source":"Crossref","is-referenced-by-count":2,"title":["New Error Bounds for Approximations from Projected Linear Equations"],"prefix":"10.1007","author":[{"given":"Huizhen","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitri P.","family":"Bertsekas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"20_CR1","volume-title":"Dynamic Programming and Optimal Control","author":"D.P. Bertsekas","year":"2007","unstructured":"Bertsekas, D.P.: Dynamic Programming and Optimal Control, 3rd edn., vol.\u00a0II. Athena Scientific, Belmont (2007)","edition":"3"},{"key":"20_CR2","volume-title":"Neuro-Dynamic Programming","author":"D.P. Bertsekas","year":"1996","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-Dynamic Programming. Athena Scientific, Belmont (1996)"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Bertsekas, D.P., Yu, H.: Projected equation methods for approximate solution of large linear systems. J. Computational and Applied Mathematics (to appear, 2008)","DOI":"10.1016\/j.cam.2008.07.037"},{"key":"20_CR4","unstructured":"Boyan, J.A.: Least-squares temporal difference learning. In: Proc. of the 16th Int. Conf. Machine Learning (1999)"},{"key":"20_CR5","unstructured":"Konda, V.R.: Actor-Critic Algorithms. Ph.D thesis. MIT, Cambridge (2002)"},{"key":"20_CR6","unstructured":"Munos, R.: Error bounds for approximate policy iteration. In: Proc. The 20th Int. Conf. Machine Learning (2003)"},{"key":"20_CR7","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1023\/A:1022192903948","volume":"13","author":"A. Nedi\u0107","year":"2003","unstructured":"Nedi\u0107, A., Bertsekas, D.P.: Least squares policy evaluation algorithms with linear function approximation. Discrete Event Dyn. Syst.\u00a013, 79\u2013110 (2003)","journal-title":"Discrete Event Dyn. Syst."},{"key":"20_CR8","first-page":"9","volume":"3","author":"R.S. Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine Learning\u00a03, 9\u201344 (1988)","journal-title":"Machine Learning"},{"key":"20_CR9","volume-title":"Reinforcement Learning","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning. MIT Press, Cambridge (1998)"},{"issue":"5","key":"20_CR10","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"J.N. Tsitsiklis","year":"1997","unstructured":"Tsitsiklis, J.N., Van Roy, B.: An analysis of temporal-difference learning with function approximation. IEEE Trans. Automat. Contr.\u00a042(5), 674\u2013690 (1997)","journal-title":"IEEE Trans. Automat. Contr."},{"issue":"11","key":"20_CR11","doi-asserted-by":"publisher","first-page":"1799","DOI":"10.1016\/S0005-1098(99)00099-0","volume":"35","author":"J.N. Tsitsiklis","year":"1999","unstructured":"Tsitsiklis, J.N., Van Roy, B.: Average cost temporal-difference learning. Automatica\u00a035(11), 1799\u20131808 (1999)","journal-title":"Automatica"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Yu, H., Bertsekas, D.P.: New error bounds for approximations from projected linear equations. Technical Report C-2008-43, University of Helsinki (2008)","DOI":"10.1109\/ALLERTON.2008.4797685"}],"container-title":["Lecture Notes in Computer Science","Recent Advances in Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-89722-4_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,15]],"date-time":"2019-05-15T14:59:06Z","timestamp":1557932346000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-89722-4_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540897217","9783540897224"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-89722-4_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2008]]}}}