{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T11:57:56Z","timestamp":1763726276851,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","license":[{"start":{"date-parts":[[2009,6,14]],"date-time":"2009-06-14T00:00:00Z","timestamp":1244937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR0011-06-1-0027"],"award-info":[{"award-number":["HR0011-06-1-0027"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000145","name":"Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-0713435"],"award-info":[{"award-number":["IIS-0713435"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2009,6,14]]},"DOI":"10.1145\/1553374.1553504","type":"proceedings-article","created":{"date-parts":[[2009,6,16]],"date-time":"2009-06-16T13:34:36Z","timestamp":1245159276000},"page":"1017-1024","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":44,"title":["Kernelized value function approximation for reinforcement learning"],"prefix":"10.1145","author":[{"given":"Gavin","family":"Taylor","sequence":"first","affiliation":[{"name":"Duke University, Durham, NC"}]},{"given":"Ronald","family":"Parr","sequence":"additional","affiliation":[{"name":"Duke University, Durham, NC"}]}],"member":"320","published-online":{"date-parts":[[2009,6,14]]},"reference":[{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/9.24227"},{"key":"e_1_3_2_1_3_1","unstructured":"Bishop C. M. (2006). Pattern Recognition and Machine Learning. Springer.   Bishop C. M. (2006). Pattern Recognition and Machine Learning . Springer."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/645528.657618"},{"volume-title":"Sparse Online Greedy Support Vector Regression. 13th European Conference on Machine Learning (pp. 84--96)","year":"2002","author":"Engel Y.","key":"e_1_3_2_1_5_1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102377"},{"key":"e_1_3_2_1_7_1","unstructured":"Farahmand A. M. Ghavamzadeh M. Szepesvari C. & Mannor S. (2008). Regularized Policy Iteration. Advances in Neural Information Processing Systems (pp. 441--448).  Farahmand A. M. Ghavamzadeh M. Szepesvari C. & Mannor S. (2008). Regularized Policy Iteration. Advances in Neural Information Processing Systems (pp. 441--448)."},{"key":"e_1_3_2_1_8_1","unstructured":"Girard A. Rasmussen C. E. Candela J. Q. & Murray-Smith R. (2003). Gaussian Process Priors with Uncertain Inputs-Application to Multiple-Step Ahead Time Series Forecasting. Advances in Neural Information Processing Systems (pp. 545--552).  Girard A. Rasmussen C. E. Candela J. Q. & Murray-Smith R. (2003). Gaussian Process Priors with Uncertain Inputs-Application to Multiple-Step Ahead Time Series Forecasting. Advances in Neural Information Processing Systems (pp. 545--552)."},{"volume-title":"Proceedings of the Twentieth International Conference on Machine Learning (pp. 424--431)","year":"2003","author":"Lagoudakis M. G.","key":"e_1_3_2_1_9_1"},{"volume-title":"echnical Report)","year":"2006","author":"Mahadevan S.","key":"e_1_3_2_1_10_1"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390251"},{"key":"e_1_3_2_1_12_1","unstructured":"Rasmussen C. E. & Kuss M. (2004). Gaussian Processes in Reinforcement Learning. Advances in Neural Information Processing Systems (pp. 751--759).  Rasmussen C. E. & Kuss M. (2004). Gaussian Processes in Reinforcement Learning. Advances in Neural Information Processing Systems (pp. 751--759)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"volume-title":"International Journal of Information Technology (pp. 54--63).","year":"2005","author":"Xu X.","key":"e_1_3_2_1_14_1"}],"event":{"name":"ICML '09: The 26th Annual International Conference on Machine Learning held in conjunction with the 2007 International Conference on Inductive Logic Programming","sponsor":["NSF","Microsoft Research Microsoft Research","MITACS"],"location":"Montreal Quebec Canada","acronym":"ICML '09"},"container-title":["Proceedings of the 26th Annual International Conference on Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1553374.1553504","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1553374.1553504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T13:29:39Z","timestamp":1750253379000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1553374.1553504"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,6,14]]},"references-count":13,"alternative-id":["10.1145\/1553374.1553504","10.1145\/1553374"],"URL":"https:\/\/doi.org\/10.1145\/1553374.1553504","relation":{},"subject":[],"published":{"date-parts":[[2009,6,14]]},"assertion":[{"value":"2009-06-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}