{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T19:50:49Z","timestamp":1762458649561},"publisher-location":"Boston, MA","reference-count":10,"publisher":"Springer US","isbn-type":[{"type":"print","value":"9780387096940"},{"type":"electronic","value":"9780387096957"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-0-387-09695-7_15","type":"book-chapter","created":{"date-parts":[[2008,8,19]],"date-time":"2008-08-19T13:40:02Z","timestamp":1219153202000},"page":"151-160","source":"Crossref","is-referenced-by-count":9,"title":["Batch Reinforcement Learning for Controlling a Mobile Wheeled Pendulum Robot"],"prefix":"10.1007","author":[{"given":"Andrea","family":"Bonarini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudio","family":"Caccia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Lazaric","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcello","family":"Restelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"doi-asserted-by":"crossref","unstructured":"Baird, L.C.: Residual algorithms: Reinforcement learning with function approximation. In: Proceedings of the 12th Intl. Conf. on Machine Learning, pp. 30-37 (1995)","key":"15_CR1_Ref","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"15_CR2_Ref","first-page":"503","volume":"6","author":"D. Ernst","year":"2005","unstructured":"Ernst, D., Geurts, P., Wehenkel, L.: Tree-based batch mode reinforcement learning. Journal of Machine Learning Research 6, 503-556 (2005)","journal-title":"Journal of Machine Learning Research"},{"key":"15_CR3_Ref","volume-title":"Approximate solutions to markov decision processes","author":"G.J. Gordon","year":"1999","unstructured":"Gordon, G.J.: Approximate solutions to markov decision processes. Ph.D. thesis, Carnegie Mellon University (1999)"},{"unstructured":"Landau, L., Lifshitz, E.M.: Mechanics, Course of Theoretical Physics, Volume 1. Pergamon Pres (1976)","key":"15_CR4_Ref"},{"key":"15_CR5_Ref","volume-title":"Modern Control Engineering","author":"K. Ogata","year":"2001","unstructured":"Ogata, K.: Modern Control Engineering (4th ed.). Prentice Hall PTR, Upper Saddle River, NJ, USA (2001)","edition":"4th ed."},{"issue":"2-3","key":"15_CR6_Ref","first-page":"161-178","volume":"49","author":"D. Ormoneit","year":"2002","unstructured":"Ormoneit, D., Sen, S.: Kernel-based reinforcement learning. Machine Learning 49(2-3), 161-178 (2002)","journal-title":"Machine Learning"},{"unstructured":"Press, W.H., Flannery, B.P., Teukolsky, S.A., Vetterling, W.T.: Numerical Recipes: The Art of Scientific Computing. Cambridge Univ. Press, New York, 1989. (1989)","key":"15_CR7_Ref"},{"key":"15_CR8_Ref","volume-title":"Energy Principles and Variational Methods in Applied Mechanics","author":"J. Reddy","year":"2002","unstructured":"Reddy, J.: Energy Principles and Variational Methods in Applied Mechanics (2nd ed.). John Wiley and Sons, Hoboken, NJ, USA (2002)","edition":"2nd ed."},{"doi-asserted-by":"crossref","unstructured":"Riedmiller, M.: Neural fitted q iteration - first experiences with a data efficient neural reinforcement learning method. In: Proceedings of European Conference on Machine Learning, pp. 317-328 (2005)","key":"15_CR9_Ref","DOI":"10.1007\/11564096_32"},{"key":"15_CR10_Ref","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, MA (1998)"}],"container-title":["IFIP \u2013 The International Federation for Information Processing","Artificial Intelligence in Theory and Practice II"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-0-387-09695-7_15.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,28]],"date-time":"2021-04-28T01:45:15Z","timestamp":1619574315000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-0-387-09695-7_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9780387096940","9780387096957"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-0-387-09695-7_15","relation":{},"ISSN":["1571-5736"],"issn-type":[{"type":"print","value":"1571-5736"}],"subject":[]}}