{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T09:47:06Z","timestamp":1743155226317,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642299452"},{"type":"electronic","value":"9783642299469"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-29946-9_29","type":"book-chapter","created":{"date-parts":[[2012,5,18]],"date-time":"2012-05-18T17:01:49Z","timestamp":1337360509000},"page":"297-308","source":"Crossref","is-referenced-by-count":1,"title":["Introduction of Fixed Mode States into Online Profit Sharing and Its Application to Waist Trajectory Generation of Biped Robot"],"prefix":"10.1007","author":[{"given":"Seiya","family":"Kuroda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuteru","family":"Miyazaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroaki","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"29_CR1","unstructured":"Chrisman, L.: Reinforcement Learning with perceptual aliasing: The Perceptual Distinctions Approach. In: Proc. of the 10th National Conf. on Artificial Intelligence, pp. 183\u2013188 (1992)"},{"key":"29_CR2","unstructured":"Hasemi, K., Suyari, H.: A Proposal of algorithm that reduces computational complexity for Online Profit Sharing. Report of the Institute of Electronics, Information and Communication Engineers NC-105(657), 103\u2013108 (2006)(in Japanese)"},{"key":"29_CR3","unstructured":"Kimura, H., Kobayashi, S.: An analysis of actor\/critic algorithm using eligibility traces: reinforcement learning with imperfect value function. In: Proc. of the 15th Int. Conf. on Machine Learning, pp. 278\u2013286 (1998)"},{"key":"29_CR4","unstructured":"Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley Professional (1989)"},{"key":"29_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1007\/978-3-540-87700-4_43","volume-title":"Parallel Problem Solving from Nature \u2013 PPSN X","author":"V. Heidrich-Meisner","year":"2008","unstructured":"Heidrich-Meisner, V., Igel, C.: Evolution Strategies for Direct Policy Search. In: Rudolph, G., Jansen, T., Lucas, S., Poloni, C., Beume, N. (eds.) PPSN 2008. LNCS, vol.\u00a05199, pp. 428\u2013437. Springer, Heidelberg (2008)"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Ikeda, K.: Exemplar-Based Direct Policy Search with Evolutionary Optimization. In: Proc. of 2005 Congress on Evolutionary Computation, CEC 2005, pp. 2357\u20132364 (2005)","DOI":"10.1109\/CEC.2005.1554988"},{"issue":"6","key":"29_CR7","doi-asserted-by":"crossref","first-page":"691","DOI":"10.20965\/jaciii.2009.p0691","volume":"13","author":"T. Matsui","year":"2009","unstructured":"Matsui, T., Goto, T., Izumi, K.: Acquiring a Government Bond Trading Strategy Using Reinforcement Learning. J. of Advanced Computational Intelligence and Intelligent Informatics\u00a013(6), 691\u2013696 (2009)","journal-title":"J. of Advanced Computational Intelligence and Intelligent Informatics"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Merrick, K., Maher, M.L.: Motivated Reinforcement Learning for Adaptive Characters in Open-Ended Simulation Games. In: Proc. of the Int. Conf. on Advanced in Computer Entertainment Technology, pp. 127\u2013134 (2007)","DOI":"10.1145\/1255047.1255073"},{"issue":"1","key":"29_CR9","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1527\/tjsai.24.104","volume":"24","author":"A. Miyamae","year":"2009","unstructured":"Miyamae, A., Sakuma, J., Ono, I., Kobayashi, S.: Instance-based Policy Learning by Real-coded Genetic Algorithms and Its Application to Control of Nonholonomic Systems. J. of the Japanese Society for Artificial Intelligence\u00a024(1), 104\u2013115 (2009) (in Japanese)","journal-title":"J. of the Japanese Society for Artificial Intelligence"},{"key":"29_CR10","unstructured":"Miyazaki, K., Yamamura, M., Kobayashi, S.: On the Rationality of Profit Sharing in Reinforcement Learning. In: Proc. of the 3rd Int. Conf. on Fuzzy Logic, Neural Nets and Soft Computing, pp. 285\u2013288 (1994)"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Miyazaki, K., Kobayashi, S.: Reinforcement Learning for Penalty Avoiding Policy Making. In: Proc. of the 2000 IEEE Int. Conf. on Systems, Man and Cybernetics, pp. 206\u2013211 (2000)","DOI":"10.1109\/ICSMC.2000.884990"},{"issue":"6","key":"29_CR12","doi-asserted-by":"crossref","first-page":"668","DOI":"10.20965\/jaciii.2007.p0668","volume":"11","author":"K. Miyazaki","year":"2007","unstructured":"Miyazaki, K., Kobayashi, S.: A Reinforcement Learning System for Penalty Avoiding in Continuous State Spaces. J. of Advanced Computational Intelligence and Intelligent Informatics\u00a011(6), 668\u2013676 (2007)","journal-title":"J. of Advanced Computational Intelligence and Intelligent Informatics"},{"issue":"6","key":"29_CR13","doi-asserted-by":"crossref","first-page":"624","DOI":"10.20965\/jaciii.2009.p0624","volume":"13","author":"K. Miyazaki","year":"2009","unstructured":"Miyazaki, K., Kobayashi, S.: Exploitation-Oriented Learning PS-r#. J. of Advanced Computational Intelligence and Intelligent Informatics\u00a013(6), 624\u2013630 (2009)","journal-title":"J. of Advanced Computational Intelligence and Intelligent Informatics"},{"key":"29_CR14","unstructured":"Randl\u03c6v, J., Alstr\u03c6m, P.: Learning to Drive a Bicycle Using Reinforcement Learning and Shaping. In: Proc. of the 15th Int. Conf. on Machine Learning, pp. 463\u2013471 (1998)"},{"issue":"3","key":"29_CR15","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1177\/105971230501300301","volume":"13","author":"P. Stone","year":"2005","unstructured":"Stone, P., Sutton, R.S., Kuhlamann, G.: Reinforcement Learning toward RoboCup Soccer Keepaway. Adaptive Behavior\u00a013(3), 0165\u20130188 (2005)","journal-title":"Adaptive Behavior"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"29_CR17","unstructured":"Sutton, R.S., McAllester, D., Singh, S.P., Mansour, Y.: Policy Gradient Methods for Reinforcement Learning with Function Approximation. In: Advances in Neural Information Processing Systems, vol.\u00a012, pp. 1057\u20131063 (2000)"},{"issue":"6","key":"29_CR18","doi-asserted-by":"crossref","first-page":"675","DOI":"10.20965\/jaciii.2009.p0675","volume":"13","author":"T. Watanabe","year":"2009","unstructured":"Watanabe, T., Miyazaki, K., Kobayashi, H.: A New Improved Penalty Avoiding Rational Policy Making Algorithm for Keepaway with Continuous State Spaces. J. of Advanced Computational Intelligence and Intelligent Informatics\u00a013(6), 675\u2013682 (2009)","journal-title":"J. of Advanced Computational Intelligence and Intelligent Informatics"},{"issue":"2","key":"29_CR19","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/s10015-004-0340-6","volume":"9","author":"J. Yoshimoto","year":"2005","unstructured":"Yoshimoto, J., Nishimura, M., Tokita, Y., Ishii, S.: Acrobot control by learning the switching of multiple controllers. J. of Artificial Life and Robotics\u00a09(2), 67\u201371 (2005)","journal-title":"J. of Artificial Life and Robotics"}],"container-title":["Lecture Notes in Computer Science","Recent Advances in Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-29946-9_29.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T09:08:01Z","timestamp":1743152881000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-29946-9_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642299452","9783642299469"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-29946-9_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}