{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T07:31:54Z","timestamp":1725521514966},"publisher-location":"Berlin, Heidelberg","reference-count":13,"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_8","type":"book-chapter","created":{"date-parts":[[2008,11,26]],"date-time":"2008-11-26T08:57:14Z","timestamp":1227689834000},"page":"96-109","source":"Crossref","is-referenced-by-count":2,"title":["Bayesian Reward Filtering"],"prefix":"10.1007","author":[{"given":"Matthieu","family":"Geist","sequence":"first","affiliation":[]},{"given":"Olivier","family":"Pietquin","sequence":"additional","affiliation":[]},{"given":"Gabriel","family":"Fricout","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"8_CR1","volume-title":"Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning)","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning), 3rd edn. The MIT Press, Cambridge (1998)","edition":"3"},{"key":"8_CR2","unstructured":"Chen, Z.: Bayesian Filtering: From Kalman Filters to Particle Filters, and Beyond. Technical report, Adaptive Systems Lab, McMaster University (2003)"},{"key":"8_CR3","unstructured":"Bellman, R.: Dynamic Programming, 6th edn. Dover Publications (1957)"},{"key":"8_CR4","unstructured":"Engel, Y.: Algorithms and Representations for Reinforcement Learning. Ph.D thesis, Hebrew University (April 2005)"},{"key":"8_CR5","unstructured":"van der Merwe, R.: Sigma-Point Kalman Filters for Probabilistic Inference in Dynamic State-Space Models. Ph.D thesis, OGI School of Science & Engineering, Oregon Health & Science University, Portland, OR, USA (April 2004)"},{"issue":"3","key":"8_CR6","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1162\/089976604772744884","volume":"16","author":"I. Szita","year":"2004","unstructured":"Szita, I., L\u0151rincz, A.: Kalman Filter Control Embedded into the Reinforcement Learning Framework. Neural Comput.\u00a016(3), 491\u2013499 (2004)","journal-title":"Neural Comput."},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Phua, C.W., Fitch, R.: Tracking Value Function Dynamics to Improve Reinforcement Learning with Piecewise Linear Function Approximation. In: ICML 2007 (2007)","DOI":"10.1145\/1273496.1273591"},{"key":"8_CR8","unstructured":"Bertsekas, D.P.: Dynamic Programming and Optimal Control, 3rd edn. Athena Scientific (1995)"},{"key":"8_CR9","volume-title":"Statisical Learning Theory","author":"V.N. Vapnik","year":"1998","unstructured":"Vapnik, V.N.: Statisical Learning Theory. John Wiley & Sons, Inc., Chichester (1998)"},{"issue":"11","key":"8_CR10","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1109\/34.888716","volume":"22","author":"M.A. Carreira-Perpinan","year":"2000","unstructured":"Carreira-Perpinan, M.A.: Mode-Finding for Mixtures of Gaussian Distributions. IEEE Transactions on Pattern Analalysis and Machine Intelligence\u00a022(11), 1318\u20131323 (2000)","journal-title":"IEEE Transactions on Pattern Analalysis and Machine Intelligence"},{"key":"8_CR11","unstructured":"Schneegass, D., Udluft, S., Martinetz, T.: Kernel Rewards Regression: an Information Efficient Batch Policy Iteration Approach. In: AIA 2006: Proceedings of the 24th IASTED international conference on Artificial intelligence and applications, Anaheim, CA, USA, pp. 428\u2013433. ACTA Press (2006)"},{"key":"8_CR12","unstructured":"Dearden, R., Friedman, N., Russell, S.J.: Bayesian Q-learning. In: Fifteenth National Conference on Artificial Intelligence, pp. 761\u2013768 (1998)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Strehl, A.L., Li, L., Wiewiora, E., Langford, J., Littman, M.L.: PAC Model-Free Reinforcement Learning. In: 23rd International Conference on Machine Learning (ICML 2006), Pittsburgh, PA, USA, pp. 881\u2013888 (2006)","DOI":"10.1145\/1143844.1143955"}],"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_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,3]],"date-time":"2019-03-03T23:48:31Z","timestamp":1551656911000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-89722-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540897217","9783540897224"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-89722-4_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2008]]}}}