{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T12:06:03Z","timestamp":1725537963936},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642042737"},{"type":"electronic","value":"9783642042744"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"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":[[2009]]},"DOI":"10.1007\/978-3-642-04274-4_8","type":"book-chapter","created":{"date-parts":[[2009,9,11]],"date-time":"2009-09-11T15:34:34Z","timestamp":1252683274000},"page":"70-79","source":"Crossref","is-referenced-by-count":4,"title":["Efficient Uncertainty Propagation for Reinforcement Learning with Limited Data"],"prefix":"10.1007","author":[{"given":"Alexander","family":"Hans","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steffen","family":"Udluft","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Calafiore, G., El Ghaoui, L.: On distributionally robust chance-constrained linear programs. In: Optimization Theory and Applications (2006)","DOI":"10.1007\/s10957-006-9084-x"},{"key":"8_CR2","doi-asserted-by":"publisher","DOI":"10.1142\/5262","volume-title":"Bayesian Reasoning in Data Analysis: A Critical Introduction","author":"G. D\u2019Agostini","year":"2003","unstructured":"D\u2019Agostini, G.: Bayesian Reasoning in Data Analysis: A Critical Introduction. World Scientific Publishing, Singapore (2003)"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Delage, E., Mannor, S.: Percentile optimization in uncertain Markov decision processes with application to efficient exploration. In: Proc. of the Int. Conf. on Machine Learning (2007)","DOI":"10.1145\/1273496.1273525"},{"key":"8_CR4","unstructured":"Engel, Y., Mannor, S., Meir, R.: Bayes meets Bellman: the Gaussian process approach to temporal difference learning. In: Proc. of the Int. Conf. on Machine Learning (2003)"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Engel, Y., Mannor, S., Meir, R.: Reinforcement learning with Gaussian processes. In: Proc. of the Int. Conf. on Machine Learning (2005)","DOI":"10.1145\/1102351.1102377"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Ghavamzadeh, M., Engel, Y.: Bayesian policy gradient algorithms. In: Advances in Neural Information Processing Systems (2006)","DOI":"10.7551\/mitpress\/7503.003.0062"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Ghavamzadeh, M., Engel, Y.: Bayesian actor-critic algorithms. In: Proc. of the Int. Conf. on Machine Learning (2007)","DOI":"10.1145\/1273496.1273534"},{"key":"8_CR8","unstructured":"Nilim, A., El Ghaoui, L.: Robustness in Markov decision problems with uncertain transition matrices. In: Advances in Neural Information Processing Systems (2003)"},{"key":"8_CR9","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"M.L. Puterman","year":"1994","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. John Wiley & Sons Canada, Ltd., Chichester (1994)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Schneegass, D., Udluft, S., Martinetz, T.: Uncertainty propagation for quality assurance in reinforcement learning. In: Proc. of the Int. Joint Conf. on Neural Networks (2008)","DOI":"10.1109\/IJCNN.2008.4634160"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Strehl, A.L., Littman, M.L.: An empirical evaluation of interval estimation for markov decision processes. In: 16th IEEE Int. Conf. on Tools with Artificial Intelligence, pp. 128\u2013135 (2004)","DOI":"10.1109\/ICTAI.2004.28"},{"key":"8_CR12","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"8_CR13","unstructured":"Tresp, V.: The wet game of chicken. Siemens AG, CT IC 4, Technical Report (1994)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks \u2013 ICANN 2009"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-04274-4_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,16]],"date-time":"2024-03-16T12:45:20Z","timestamp":1710593120000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-04274-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642042737","9783642042744"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-04274-4_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}