{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T00:27:24Z","timestamp":1725755244543},"publisher-location":"Berlin, Heidelberg","reference-count":18,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642418211"},{"type":"electronic","value":"9783642418228"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-41822-8_25","type":"book-chapter","created":{"date-parts":[[2013,11,4]],"date-time":"2013-11-04T16:34:05Z","timestamp":1383582845000},"page":"198-205","source":"Crossref","is-referenced-by-count":1,"title":["Qualitative Transfer for Reinforcement Learning with Continuous State and Action Spaces"],"prefix":"10.1007","author":[{"given":"Esteban O.","family":"Garcia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrique Munoz","family":"de Cote","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduardo F.","family":"Morales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Deisenroth, M.P., Peters, J., Rasmussen, C.E.: Approximate dynamic programming with Gaussian processes. In: American Control Conference, pp. 4480\u20134485 (2008)","DOI":"10.1109\/ACC.2008.4587201"},{"key":"25_CR2","unstructured":"Deisenroth, M.P., Rasmussen, C.E.: PILCO: A Model-Based and Data-Efficient Approach to Policy Search. In: ICML 2011, pp. 465\u2013472 (2011)"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Deisenroth, M.P., Rasmussen, C.E., Fox, D.: Learning to control a low-cost manipulator using data-efficient reinforcement learning. In: Proceedings of Robotics: Science and Systems, Los Angeles, CA, USA (2011)","DOI":"10.15607\/RSS.2011.VII.008"},{"key":"25_CR4","unstructured":"Deisenroth, M.P., Rasmussen, C.E., Peters, J.: Model-based reinforcement learning with continuous states and actions. In: 16th European Symposium on Artificial Neural Networks, pp. 19\u201324 ( April 2008)"},{"issue":"1","key":"25_CR5","first-page":"154","volume":"20","author":"Y. Engel","year":"2003","unstructured":"Engel, Y., Mannor, S., Meir, R.: Bayes meets Bellman: The Gaussian process approach to temporal difference learning. ICML\u00a020(1), 154 (2003)","journal-title":"ICML"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Engel, Y., Mannor, S., Meir, R.: Reinforcement learning with Gaussian processes. In: ICML 2005, pp. 201\u2013208 (2005)","DOI":"10.1145\/1102351.1102377"},{"key":"25_CR7","unstructured":"Hasselt, H.V.: Insights in Reinforcement Learning Formal analysis and empirical evaluation of temporal-difference learning algorithms (2011)"},{"key":"25_CR8","unstructured":"Hasselt, H.V.: Reinforcement Learning in Continuous State and Action Spaces. In: Reinforcement Learning: State of the Art (2011)"},{"key":"25_CR9","unstructured":"Lazaric, A., Restelli, M., Bonarini, A.: Reinforcement learning in continuous action spaces through sequential monte carlo methods. In: Advances in Neural Information Processing Systems (2007)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Lazaric, A., Restelli, M., Bonarini, A.: Transfer of samples in batch reinforcement learning. In: Proceedings of the 25th International Conference on Machine Learning, ICML 2008, pp. 544\u2013551 (2008)","DOI":"10.1145\/1390156.1390225"},{"issue":"8","key":"25_CR11","doi-asserted-by":"publisher","first-page":"1251","DOI":"10.1016\/j.neucom.2010.07.027","volume":"74","author":"J.A. Mart\u00edn","year":"2011","unstructured":"Mart\u00edn, J.A., de Lope, H.J., Maravall, D.: Robust high performance reinforcement learning through weighted k-nearest neighbors. Neurocomputing\u00a074(8), 1251\u20131259 (2011)","journal-title":"Neurocomputing"},{"key":"25_CR12","unstructured":"Murray-Smith, R., Sbarbaro, D.: Nonlinear adaptive control using non-parametric Gaussian process prior models. In: 15TH IFAC, pp. 21\u201326 (July 2002)"},{"key":"25_CR13","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/978-3-540-89722-4_18","volume-title":"Recent Advances in Reinforcement Learning","author":"C.E. Rasmussen","year":"2008","unstructured":"Rasmussen, C.E., Deisenroth, M.P.: Probabilistic inference for fast learning in control. In: Girgin, S., Loth, M., Munos, R., Preux, P., Ryabko, D. (eds.) EWRL 2008. LNCS (LNAI), vol.\u00a05323, pp. 229\u2013242. Springer, Heidelberg (2008)"},{"key":"25_CR14","unstructured":"Rasmussen, C.E., Kuss, M.: Gaussian Processes in Reinforcement Learning. Advances in Neural Information Processing Systems 16, 16 (2004)"},{"issue":"2","key":"25_CR15","first-page":"69","volume":"14","author":"C.E. Rasmussen","year":"2006","unstructured":"Rasmussen, C.E., Williams, C.: Gaussian Processes for Machine Learning. International Journal of Neural Systems\u00a014(2), 69\u2013106 (2006)","journal-title":"International Journal of Neural Systems"},{"key":"25_CR16","unstructured":"Sutton, R., Barto, A.G.: Introduction to Reinforcement Learning. MIT Press (1998)"},{"key":"25_CR17","unstructured":"Taylor, M.E., Jong, N.K., Stone, P.: Transferring Instances for Model-Based Reinforcement Learning. Machine Learning (September 2008)"},{"key":"25_CR18","first-page":"1633","volume":"10","author":"M.E. Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer Learning for Reinforcement Learning Domains: A Survey. Journal of Machine Learning Research\u00a010, 1633\u20131685 (2009)","journal-title":"Journal of Machine Learning Research"}],"container-title":["Lecture Notes in Computer Science","Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-41822-8_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,24]],"date-time":"2019-05-24T02:41:24Z","timestamp":1558665684000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-41822-8_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642418211","9783642418228"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-41822-8_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}