{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T21:05:56Z","timestamp":1725570356285},"publisher-location":"Berlin, Heidelberg","reference-count":7,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540404088"},{"type":"electronic","value":"9783540449898"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2003]]},"DOI":"10.1007\/3-540-44989-2_94","type":"book-chapter","created":{"date-parts":[[2010,11,19]],"date-time":"2010-11-19T22:10:02Z","timestamp":1290204602000},"page":"786-793","source":"Crossref","is-referenced-by-count":1,"title":["Acceleration of Game Learning with Prediction-Based Reinforcement Learning \u2014 Toward the Emergence of Planning Behavior \u2014"],"prefix":"10.1007","author":[{"given":"Yu","family":"Ohigashi","sequence":"first","affiliation":[]},{"given":"Takashi","family":"Omori","sequence":"additional","affiliation":[]},{"given":"Koji","family":"Morikawa","sequence":"additional","affiliation":[]},{"given":"Natsuki","family":"Oka","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2003,6,18]]},"reference":[{"key":"94_CR1","first-page":"9","volume":"3","author":"R.S. Sutton","year":"1988","unstructured":"Sutton, R.S., Learning to predict by the method of temporal differences, Machine Learning, 3, pp. 9\u201344, 1988.","journal-title":"Machine Learning"},{"key":"94_CR2","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S. and Barto, A.G., Reinforcement Learning: An Introduction, MIT Press, Cambridge, MA, 1998."},{"unstructured":"Yasuharu Koike and Kenji Doya, A Driver Model Based on Reinforcement Learning with Multiple-Step State Estimation, IEICE Transactions, Vol. J84-D-II,No. 2, pp. 370\u2013379.","key":"94_CR3"},{"unstructured":"Kazuyuki Samejima, Ken\u2019ichi Katagiri, Kenji Doya and Mituo Kawato, Multiple Model-based Reinforcement Learning of Nonlinear Control, IEICE Transactions, Vol. J83-DII,No. 9, pp. 2092\u20132106.","key":"94_CR4"},{"doi-asserted-by":"crossref","unstructured":"Christian Balkenius and Jan Moren, Dynamics of a Classical Conditioning Model, ICANN 98, Perspectives in Neural Computing, Springer-Verlag, 1999.","key":"94_CR5","DOI":"10.1007\/978-1-4471-1599-1_65"},{"unstructured":"Watkins, C.J.C.H.(1989). Learning from Delayed Rewards. Ph.D. thesis, Cambridge University.","key":"94_CR6"},{"unstructured":"Rummery, G.A., and Niranjan, M. (1994). On-line Q-learning using connectinist systems. Technical Report CUED\/F-INFENG\/TR 166. Engineering Department, Cambridge University.","key":"94_CR7"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Neural Information Processing \u2014 ICANN\/ICONIP 2003"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-44989-2_94","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,6]],"date-time":"2019-06-06T11:43:36Z","timestamp":1559821416000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-44989-2_94"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540404088","9783540449898"],"references-count":7,"URL":"https:\/\/doi.org\/10.1007\/3-540-44989-2_94","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2003]]}}}