{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T19:09:08Z","timestamp":1725563348246},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642159381"},{"type":"electronic","value":"9783642159398"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-15939-8_30","type":"book-chapter","created":{"date-parts":[[2010,8,18]],"date-time":"2010-08-18T03:54:25Z","timestamp":1282103665000},"page":"467-482","source":"Crossref","is-referenced-by-count":7,"title":["Incorporating Domain Models into Bayesian Optimization for RL"],"prefix":"10.1007","author":[{"given":"Aaron","family":"Wilson","sequence":"first","affiliation":[]},{"given":"Alan","family":"Fern","sequence":"additional","affiliation":[]},{"given":"Prasad","family":"Tadepalli","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"30_CR1","first-page":"944","volume-title":"IJCAI\u201907: Proceedings of the 20th International Joint Conference on Artifical Intelligence","author":"D. Lizotte","year":"2007","unstructured":"Lizotte, D., Wang, T., Bowling, M., Schuurmans, D.: Automatic gait optimization with gaussian process regression. In: IJCAI\u201907: Proceedings of the 20th International Joint Conference on Artifical Intelligence, pp. 944\u2013949. Morgan Kaufmann, San Francisco (2007)"},{"key":"30_CR2","unstructured":"Lizotte, D.: Practical Bayesian Optimization. PhD thesis, University of Alberta (2008)"},{"key":"30_CR3","unstructured":"Brochu, E., Cora, V., de Freitas, N.: A tutorial on bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. Technical Report TR-2009-023 (2009)"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Engel, Y., Mannor, S., Meir, R.: Reinforcement learning with Gaussian processes. In: International Conference on Machine Learning, pp. 201\u2013208 (2005)","DOI":"10.1145\/1102351.1102377"},{"key":"30_CR5","unstructured":"Dearden, R., Friedman, N., Andre, D.: Model based Bayesian exploration. In: UAI (1999)"},{"key":"30_CR6","unstructured":"Strens, M.J.A.: A Bayesian framework for reinforcement learning. In: International Conference on Machine Learning, pp. 943\u2013950 (2000)"},{"key":"30_CR7","unstructured":"Duff, M.: Design for an optimal probe. In: International Conference on Machine Learning (2003)"},{"key":"30_CR8","doi-asserted-by":"publisher","first-page":"2003","DOI":"10.1162\/jmlr.2003.4.6.1107","volume":"4","author":"M.G. Lagoudakis","year":"2003","unstructured":"Lagoudakis, M.G., Parr, R., Bartlett, L.: Least-squares policy iteration. Journal of Machine Learning Research\u00a04 (2003)","journal-title":"Journal of Machine Learning Research"},{"key":"30_CR9","volume-title":"Reinforcement Learning: An Introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"issue":"1","key":"30_CR10","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1613\/jair.807","volume":"15","author":"J. Baxter","year":"2001","unstructured":"Baxter, J., Bartlett, P.L., Weaver, L.: Experiments with infinite-horizon, policy-gradient estimation. Journal of Artificial Intelligence Research\u00a015(1), 351\u2013381 (2001)","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"4","key":"30_CR11","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/BF01099263","volume":"4","author":"J. Mockus","year":"1994","unstructured":"Mockus, J.: Application of bayesian approach to numerical methods of global and stochastic optimization. Global Optimization\u00a04(4), 347\u2013365 (1994)","journal-title":"Global Optimization"},{"issue":"11","key":"30_CR12","doi-asserted-by":"publisher","first-page":"3088","DOI":"10.1016\/j.jspi.2010.04.018","volume":"140","author":"E. Vazquez","year":"2010","unstructured":"Vazquez, E., Bect, J.: Convergence properties of the expected improvement algorithm with fixed mean and covariance functions. Journal of Statistical Planning and Inference\u00a0140(11), 3088\u20133095 (2010)","journal-title":"Journal of Statistical Planning and Inference"},{"key":"30_CR13","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3206.001.0001","volume-title":"Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)","author":"C.E. Rasmussen","year":"2005","unstructured":"Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning). The MIT Press, Cambridge (2005)"},{"issue":"1","key":"30_CR14","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/BF00941892","volume":"79","author":"D.R. Jones","year":"1993","unstructured":"Jones, D.R., Perttunen, C.D., Stuckman, B.E.: Lipschitzian optimization without the lipschitz constant. J. Optim. Theory Appl.\u00a079(1), 157\u2013181 (1993)","journal-title":"J. Optim. Theory Appl."}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-15939-8_30.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T21:43:10Z","timestamp":1606167790000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-15939-8_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642159381","9783642159398"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-15939-8_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}