{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:04:43Z","timestamp":1742958283497,"version":"3.40.3"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319466743"},{"type":"electronic","value":"9783319466750"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-46675-0_25","type":"book-chapter","created":{"date-parts":[[2016,9,28]],"date-time":"2016-09-28T09:55:47Z","timestamp":1475056547000},"page":"221-230","source":"Crossref","is-referenced-by-count":0,"title":["Sparse Kernel-Based Least Squares Temporal Difference with Prioritized Sweeping"],"prefix":"10.1007","author":[{"given":"Cijia","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinghong","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haijun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,29]]},"reference":[{"key":"25_CR1","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"25_CR2","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","volume-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators","author":"L Busoniu","year":"2010","unstructured":"Busoniu, L., Babuska, R., Schutter, B.D., Ernst, D.: Reinforcement Learning and Dynamic Programming Using Function Approximators. CRC Press, Boca Raton (2010)"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Wiering, M., van Otterlo, M.: Reinforcement learning: state-of-the-art. Phillip Journal Fr Restaurative Zahnmedizin (2012)","DOI":"10.1007\/978-3-642-27645-3"},{"key":"25_CR4","series-title":"Adaptation, Learning, and Optimization","first-page":"205","volume-title":"Reinforcement Learning: State-of-the-Art","author":"H Hasselt van","year":"2012","unstructured":"van Hasselt, H.: Reinforcement learning in continuous state and action spaces. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning. ALO, vol. 12, pp. 205\u2013248. Springer, Heidelberg (2012)"},{"issue":"9","key":"25_CR5","first-page":"54","volume":"11","author":"X Xu","year":"2005","unstructured":"Xu, X., Xie, X., Hu, D.: Kernel least-squares temporal difference learning. Int. J. Inf. Technol. 11(9), 54\u201363 (2005)","journal-title":"Int. J. Inf. Technol."},{"issue":"4","key":"25_CR6","doi-asserted-by":"crossref","first-page":"973","DOI":"10.1109\/TNN.2007.899161","volume":"18","author":"X Xu","year":"2007","unstructured":"Xu, X., Hu, D.: Kernel-based least squares policy iteration for reinforcement learning. IEEE Trans. Neural Netw. 18(4), 973\u2013992 (2007)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"1","key":"25_CR7","first-page":"103","volume":"13","author":"AW Moore","year":"1993","unstructured":"Moore, A.W., Atkeson, C.G.: Prioritized sweeping: reinforcement learning with less data and less time. Mach. Learn. 13(1), 103\u2013130 (1993)","journal-title":"Mach. Learn."},{"key":"25_CR8","unstructured":"Sutton, R.S., Szepesvari, C., Geramifard, A., Bowling, M.P.: Dyna-style planning with linear function approximation and prioritized sweeping. In: Conference on Uncertainty in Artificial Intelligence (2008)"},{"issue":"6","key":"25_CR9","first-page":"1107","volume":"4","author":"MG Lagoudakis","year":"2010","unstructured":"Lagoudakis, M.G., Parr, R.: Least-squares policy iteration. J. Mach. Learn. Res. 4(6), 1107\u20131149 (2010)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"25_CR10","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1109\/JAS.2014.7004685","volume":"1","author":"Q Liu","year":"2014","unstructured":"Liu, Q., Zhou, X., Zhu, F., Fu, Q., Fu, Y.: Experience replay for least-squares policy iteration. IEEE\/CAA J. Autom. Sin. 1(3), 274\u2013281 (2014). IEEE","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"25_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/11881070_8","volume-title":"Advances in Natural Computation","author":"X Xu","year":"2006","unstructured":"Xu, X.: A sparse kernel-based least-squares temporal difference algorithm for reinforcement learning. In: Jiao, L., Wang, L., Gao, X., Liu, J., Wu, F. (eds.) ICNC 2006. LNCS, vol. 4221, pp. 47\u201356. Springer, Heidelberg (2006). doi: 10.1007\/11881070_8"},{"key":"25_CR12","unstructured":"Jong, N., Stone, P.: Kernel-based models for reinforcement learning. In: ICML Workshop on Kernel Machines and Reinforcement Learning (2006)"},{"key":"25_CR13","unstructured":"Engel, Y., Mannor, S., Meir, R.: Bayes meets Bellman: the Gaussian process approach to temporal difference learning. In: 20th International Conference on Machine Learning, pp. 154\u2013161. American Association for Artificial Intelligence (2003)"},{"issue":"1","key":"25_CR14","first-page":"3041","volume":"13","author":"A Lazaric","year":"2012","unstructured":"Lazaric, A., Ghavamzadeh, M., Munos, R.: Finite-sample analysis of least-squares policy iteration. J. Mach. Learn. Res. 13(1), 3041\u20133074 (2012). Microtome Publishing","journal-title":"J. Mach. Learn. Res."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46675-0_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T19:52:49Z","timestamp":1498333969000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46675-0_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319466743","9783319466750"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46675-0_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}