{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T06:53:49Z","timestamp":1751525629719},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642332654"},{"type":"electronic","value":"9783642332661"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33266-1_15","type":"book-chapter","created":{"date-parts":[[2012,9,18]],"date-time":"2012-09-18T19:42:31Z","timestamp":1347997351000},"page":"116-123","source":"Crossref","is-referenced-by-count":5,"title":["Control of a Free-Falling Cat by Policy-Based Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Daichi","family":"Nakano","sequence":"first","affiliation":[]},{"given":"Shin-ichi","family":"Maeda","sequence":"additional","affiliation":[]},{"given":"Shin","family":"Ishii","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"15_CR1","first-page":"521","volume":"11","author":"Y. Nakamura","year":"1993","unstructured":"Nakamura, Y.: Nonholonomic robot systems, Part 1: what\u2019s a nonholonomic robot? Journal of RSJ\u00a011, 521\u2013528 (1993)","journal-title":"Journal of RSJ"},{"key":"15_CR2","first-page":"181","volume":"27","author":"R.W. Brockett","year":"1983","unstructured":"Brockett, R.W.: Asymptotic stability and feedback stabilization. Progress in Mathematics\u00a027, 181\u2013208 (1983)","journal-title":"Progress in Mathematics"},{"unstructured":"Mita, T.: Introduction to nonlinear control Theory-Skill control of underactuated robots. SHOKODO Co., Ltd. (2000) (in Japanese)","key":"15_CR3"},{"key":"15_CR4","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1109\/9.277235","volume":"38","author":"R.M. Murray","year":"1993","unstructured":"Murray, R.M., Sastry, S.S.: Nonholonomic motion planning: steering using sinusoids. IEEE Transactions on Automatic Control\u00a038, 700\u2013716 (1993)","journal-title":"IEEE Transactions on Automatic Control"},{"key":"15_CR5","first-page":"745","volume":"25","author":"S. Holamoto","year":"1993","unstructured":"Holamoto, S., Funasako, T.: Feedback control of a planar space robot using a moving manifold. Journal of RSJ\u00a025, 745\u2013751 (1993)","journal-title":"Journal of RSJ"},{"key":"15_CR6","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1016\/j.neunet.2008.02.003","volume":"21","author":"J. Peters","year":"2008","unstructured":"Peters, J., Schaal, S.: Reinforcement learning of motor skills with policy gradients. Neural Networks\u00a021, 682\u2013697 (2008)","journal-title":"Neural Networks"},{"key":"15_CR7","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1527\/tjsai.24.104","volume":"24","author":"A. Miyamae","year":"2009","unstructured":"Miyamae, A., et al.: Instance-based policy learning by real-coded genetic algorithms and its application to control of nonholonomic systems. Transactions of the Japanese Society for Artificial Intelligence\u00a024, 104\u2013115 (2009)","journal-title":"Transactions of the Japanese Society for Artificial Intelligence"},{"key":"15_CR8","doi-asserted-by":"crossref","first-page":"1344","DOI":"10.9746\/sicetr1965.42.1344","volume":"42","author":"C. Tsuchiya","year":"2006","unstructured":"Tsuchiya, C., et al.: SLIP: A sophisticated learner for instance-based policy using hybrid GA. Transactions of SICE\u00a042, 1344\u20131352 (2006)","journal-title":"Transactions of SICE"},{"key":"15_CR9","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1109\/70.86080","volume":"7","author":"Y. Nakamura","year":"1991","unstructured":"Nakamura, Y., Mukherjee, R.: Nonholonomic path planning of space robots via a bidirectional approach. IEEE Transactions on Robotics and Automation\u00a07, 500\u2013514 (1991)","journal-title":"IEEE Transactions on Robotics and Automation"},{"key":"15_CR10","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","volume":"15","author":"J. Baxter","year":"2001","unstructured":"Baxter, J., Bartlett, P.L.: Infinite-horizon policy-gradient estimation. Journal of Artificial Intelligence Research\u00a015, 319\u2013350 (2001)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"15_CR11","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/s10483-007-0505-z","volume":"28","author":"X. Ge","year":"2007","unstructured":"Ge, X., Chen, L.: Optimal control of nonholonomic motion planning for a free-falling cat. Applied Mathematics and Mechanics\u00a028, 601\u2013607 (2007)","journal-title":"Applied Mathematics and Mechanics"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2012"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33266-1_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,7]],"date-time":"2019-05-07T07:36:12Z","timestamp":1557214572000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33266-1_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642332654","9783642332661"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33266-1_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}