{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:25:43Z","timestamp":1752229543763},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540628583"},{"type":"electronic","value":"9783540687085"}],"license":[{"start":{"date-parts":[[1997,1,1]],"date-time":"1997-01-01T00:00:00Z","timestamp":852076800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1997]]},"DOI":"10.1007\/3-540-62858-4_82","type":"book-chapter","created":{"date-parts":[[2012,2,26]],"date-time":"2012-02-26T17:52:09Z","timestamp":1330278729000},"page":"170-182","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Finite-Element methods with local triangulation refinement for continuous reinforcement learning problems"],"prefix":"10.1007","author":[{"given":"R\u00e9mi","family":"Munos","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2005,6,2]]},"reference":[{"key":"16_CR1","unstructured":"Leemon Baird. Residual algorithms: Reinforcement learning with function approximation. Machine Learning: proceedings of the Twelfth International Conference, 1995."},{"key":"16_CR2","volume-title":"Neural networks for control","author":"A. G. Barto","year":"1990","unstructured":"Andrew G. Barto. Neural networks for control. W.T. Miller, R.S.Sutton, P.J. Werbos editors. MIT press, Cambridge, Massachussetts, 1990."},{"key":"16_CR3","unstructured":"Andrew G. Barto, Steven J. Bradtke, and Satinder P. Singh. Real-time learning and control using asynchronous dynamic programming. Technical Report 91-57, Computer Science Department, University of Massachusetts, 1991."},{"key":"16_CR4","unstructured":"Dimitri P. Bertsekas. Dynamic Programming: Deterministic and Stochastic Models. Prentice Hall, 1987."},{"key":"16_CR5","unstructured":"J.A. Boyan and A.W. Moore. Generalization in reinforcement learning: Safely approximating the value function. Advances in Neural Information Processing Systems, 7, 1995."},{"key":"16_CR6","unstructured":"Wendell H. Fleming and H. Mete Soner. Controlled Markov Processes and Viscosity Solutions. Applications of Mathematics. Springer-Verlag, 1993."},{"key":"16_CR7","volume-title":"PhD thesis","author":"V. Gullapalli","year":"1992","unstructured":"Vijay Gullapalli. Reinforcement Learning and its application to control. PhD thesis, University of Massachussetts, Amherst., 1992."},{"key":"16_CR8","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/105971239500400102","volume":"4","author":"M. E. Harmon","year":"1996","unstructured":"Mance E. Harmon, Leemon C. Baird, and A. Harry Klopf. Reinforcement learning applied to a differential game. Adaptive Behavior, 4:3\u201328, 1996.","journal-title":"Adaptive Behavior"},{"key":"16_CR9","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1137\/0328056","volume":"28","author":"H. J. Kushner","year":"1990","unstructured":"Harold J. Kushner. Numerical methods for stochastic control problems in continuous time. SIAM J. Control and Optimization, 28:999\u20131048, 1990.","journal-title":"SIAM J. Control and Optimization"},{"key":"16_CR10","volume-title":"PhD thesis","author":"L. Lin","year":"1993","unstructured":"Long-Ji Lin. Reinforcement Learning for Robots using Neural Networks. PhD thesis, Carnegie Mellon University, Pittsburg, Pennsylvania, 1993."},{"key":"16_CR11","unstructured":"Terje Midtbo. Spatial Modelling by Delaunay Networks of Two and Three Dimensions. PhD thesis, Norwegian Institute of Technology, 1993."},{"key":"16_CR12","unstructured":"R. Munos. A convergent reinforcement learning algorithm in the continuous case: the finite-element reinforcement learning. International Conference on Machine Learning, 1996."},{"key":"16_CR13","unstructured":"Ann Now. Fuzzy reinforcement learning. an overview. Advances in Fuzzy Theory and Technology, 1995."},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Jim Ruppert. A delaunay refinement algorithm for quality 2-dimensional mesh generation. Journal of Algorithms, 1994.","DOI":"10.1006\/jagm.1995.1021"},{"key":"16_CR15","unstructured":"Richard S. Sutton. Generalization in reinforcement learning: Successful examples using sparse coarse coding. Advances in Neural Information Processing Systems, 8, 1996."},{"key":"16_CR16","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1093\/comjnl\/24.2.167","volume":"24","author":"D.F. Watson","year":"1981","unstructured":"D.F. Watson. Computing the n-dimensional delaunay tessellation with application to voronoi polytopes. The Computer Journal, 24:167\u2013172, 1981.","journal-title":"The Computer Journal"},{"key":"16_CR17","unstructured":"Christopher J.C.H. Watkins. Learning from delayed reward. PhD thesis, Cambridge University, 1989."}],"container-title":["Lecture Notes in Computer Science","Machine Learning: ECML-97"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-62858-4_82","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,19]],"date-time":"2019-05-19T08:23:51Z","timestamp":1558254231000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-62858-4_82"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1997]]},"ISBN":["9783540628583","9783540687085"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/3-540-62858-4_82","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[1997]]},"assertion":[{"value":"2 June 2005","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}