{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T06:40:58Z","timestamp":1725518458806},"publisher-location":"Berlin, Heidelberg","reference-count":10,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540875352"},{"type":"electronic","value":"9783540875369"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-87536-9_38","type":"book-chapter","created":{"date-parts":[[2008,9,5]],"date-time":"2008-09-05T15:23:30Z","timestamp":1220628210000},"page":"367-376","source":"Crossref","is-referenced-by-count":1,"title":["Self-organized\u00a0Reinforcement\u00a0Learning Based\u00a0on\u00a0Policy\u00a0Gradient in\u00a0Nonstationary\u00a0Environments"],"prefix":"10.1007","author":[{"given":"Yu","family":"Hiei","sequence":"first","affiliation":[]},{"given":"Takeshi","family":"Mori","sequence":"additional","affiliation":[]},{"given":"Shin","family":"Ishii","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"7-8","key":"38_CR1","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1016\/S0893-6080(98)00066-5","volume":"11","author":"D.M. Wolpert","year":"1998","unstructured":"Wolpert, D.M., Kawato, M.: Multiple paired forward and inverse models for motor control. Neural Networks\u00a011(7-8), 1317\u20131329 (1998)","journal-title":"Neural Networks"},{"issue":"10","key":"38_CR2","doi-asserted-by":"publisher","first-page":"2201","DOI":"10.1162\/089976601750541778","volume":"13","author":"M. Haruno","year":"2001","unstructured":"Haruno, M., Wolpert, D.M., Kawato, M.: MOSAIC Model for Sensorimotor Learning and Control. Neural Computation\u00a013(10), 2201\u20132220 (2001)","journal-title":"Neural Computation"},{"issue":"6","key":"38_CR3","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1162\/089976602753712972","volume":"14","author":"K. Doya","year":"2002","unstructured":"Doya, K., Samejima, K., Katagiri, K., Kawato, M.: Multiple Model-Based Reinforcement Learning. Neural Computation\u00a014(6), 1347\u20131369 (2002)","journal-title":"Neural Computation"},{"key":"38_CR4","volume-title":"An introduction to reinforcement learning","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: An introduction to reinforcement learning. MIT Press, Cambridge (1998)"},{"key":"38_CR5","first-page":"229","volume":"8","author":"R.J. Williams","year":"1992","unstructured":"Williams, R.J.: Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning. Machine Learning\u00a08, 229\u2013256 (1992)","journal-title":"Machine Learning"},{"issue":"9","key":"38_CR6","doi-asserted-by":"publisher","first-page":"1464","DOI":"10.1109\/5.58325","volume":"78","author":"T. Kohonen","year":"1990","unstructured":"Kohonen, T.: The self-organized map. Proc. IEEE\u00a078(9), 1464\u20131480 (1990)","journal-title":"Proc. IEEE"},{"key":"38_CR7","first-page":"323","volume":"8","author":"S.P. Singh","year":"1992","unstructured":"Singh, S.P.: Transfer of Learning by Composing Solutions of Elemental Sequential Tasks. Machine Learning\u00a08, 323\u2013339 (1992)","journal-title":"Machine Learning"},{"issue":"1-2","key":"38_CR8","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R. Sutton","year":"1999","unstructured":"Sutton, R., Precup, D., Singh, S.: Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning. Artif. Intell.\u00a0112(1-2), 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"issue":"8","key":"38_CR9","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1162\/089976602760128018","volume":"14","author":"G.E. Hinton","year":"2002","unstructured":"Hinton, G.E.: Training Products of Experts by Minimizing Contrastive Divergence. Neural Computation\u00a014(8), 1771\u20131800 (2002)","journal-title":"Neural Computation"},{"key":"38_CR10","unstructured":"Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic model for segmenting and labeling sequence data. In: Proc. 18th International Conf. on Machine Learning (2001)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks - ICANN 2008"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-87536-9_38.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T12:00:58Z","timestamp":1619524858000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-87536-9_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540875352","9783540875369"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-87536-9_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}