{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T13:21:28Z","timestamp":1725542488039},"publisher-location":"Berlin, Heidelberg","reference-count":6,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642106767"},{"type":"electronic","value":"9783642106774"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-10677-4_67","type":"book-chapter","created":{"date-parts":[[2009,12,14]],"date-time":"2009-12-14T17:12:56Z","timestamp":1260810776000},"page":"590-597","source":"Crossref","is-referenced-by-count":0,"title":["Robust Approximation in Decomposed Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Takeshi","family":"Mori","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shin","family":"Ishii","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"67_CR1","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1109\/9.24227","volume":"34","author":"D. Bertsekas","year":"1989","unstructured":"Bertsekas, D., Casta\u00f1on, D.: Adaptive aggregation methods for infinite horizon dynamic programming. IEEE Transactions on Automatic Control\u00a034, 589\u2013598 (1989)","journal-title":"IEEE Transactions on Automatic Control"},{"issue":"2","key":"67_CR2","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1023\/A:1018056104778","volume":"22","author":"S.J. Bradtke","year":"1996","unstructured":"Bradtke, S.J., Barto, A.G.: Linear least-squares algorithms for temporal difference learning. Machine Learning\u00a022(2), 33\u201357 (1996)","journal-title":"Machine Learning"},{"key":"67_CR3","doi-asserted-by":"crossref","unstructured":"Dasgupta, M., Mishra, S., Hill, N.: Least absolute deviation estimation of linear economic models: A literature review. Munich Personal PePEc Archive\u00a01781 (2004)","DOI":"10.2139\/ssrn.552502"},{"key":"67_CR4","doi-asserted-by":"crossref","unstructured":"Keller, P.W., Mannor, S., Precup, D.: Automatic basis function construction for approximate dynamic programming and reinforcement learning. In: Proceedings of the Twenty-third International Conference on Machine Learning (2006)","DOI":"10.1145\/1143844.1143901"},{"key":"67_CR5","doi-asserted-by":"crossref","unstructured":"Mori, T., Ishii, S.: An additive reinforcement learning. In: The Ninteenth International Conference on Artificial Neural Networks (2009)","DOI":"10.1007\/978-3-642-04274-4_63"},{"key":"67_CR6","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)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-10677-4_67.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T21:33:26Z","timestamp":1606167206000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-10677-4_67"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642106767","9783642106774"],"references-count":6,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-10677-4_67","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}