{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T10:46:13Z","timestamp":1725533173123},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642024771"},{"type":"electronic","value":"9783642024788"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-02478-8_73","type":"book-chapter","created":{"date-parts":[[2009,6,5]],"date-time":"2009-06-05T18:46:41Z","timestamp":1244227601000},"page":"577-584","source":"Crossref","is-referenced-by-count":0,"title":["Two Steps Reinforcement Learning in Continuous Reinforcement Learning Tasks"],"prefix":"10.1007","author":[{"given":"Iv\u00e1n","family":"L\u00f3pez-Bueno","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"Garc\u00eda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fernando","family":"Fern\u00e1ndez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"73_CR1","volume-title":"Dynamic programming","author":"R. Bellman","year":"1957","unstructured":"Bellman, R.: Dynamic programming. Princeton University Press, Princeton (1957)"},{"key":"73_CR2","unstructured":"Boyan, J.A., Moore, A.W.: Generalization in reinforcement learning: Safely approximating the value function. Adva. Neural Inform. Process. Syst.\u00a07 (1995)"},{"key":"73_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1007\/3-540-45327-X_24","volume-title":"RoboCup-99: Robot Soccer World Cup III","author":"F. Fern\u00e1ndez","year":"2000","unstructured":"Fern\u00e1ndez, F., Borrajo, D.: VQQL. Applying vector quantization to reinforcement learning. In: Veloso, M.M., Pagello, E., Kitano, H. (eds.) RoboCup 1999. LNCS, vol.\u00a01856, pp. 292\u2013303. Springer, Heidelberg (2000)"},{"key":"73_CR4","unstructured":"Frank, E., Witten, I.H.: Generating Accurate Rule Sets Without Global Optimization. In: Fifteenth International Conference on Machine Learning, pp. 144\u2013151 (1998)"},{"key":"73_CR5","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1002\/int.20255","volume":"23","author":"F. Fern\u00e1ndez","year":"2008","unstructured":"Fern\u00e1ndez, F., Borrajo, D.: Two steps reinforcement learning. Internation Journal of Intelligent Systems\u00a023, 213\u2013245 (2008)","journal-title":"Internation Journal of Intelligent Systems"},{"key":"73_CR6","doi-asserted-by":"crossref","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement Learning: A Survay (1996)","DOI":"10.1613\/jair.301"},{"key":"73_CR7","unstructured":"Smart, W.D.: Making reinforcement learning work on real robots. PhD thesis, Department of Computer Science at Brown University, Providence, RI (May 2002)"},{"key":"73_CR8","doi-asserted-by":"crossref","unstructured":"Stone, P., Sutton, R., Kuhlmann, G.: Reinforcement Learning for RoboCup-Soccer Keepaway. Adaptive Behaviour\u00a013(3) (2005)","DOI":"10.1177\/105971230501300301"},{"key":"73_CR9","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 (1998)"},{"key":"73_CR10","volume-title":"Data Mining: Practical Machine Learning Tools and Techniques","author":"E. Frank","year":"2005","unstructured":"Frank, E., Witten, I.H.: Data Mining: Practical Machine Learning Tools and Techniques, 2nd edn. Morgan Kaufmann, San Francisco (2005)","edition":"2"},{"key":"73_CR11","first-page":"291","volume-title":"Machine Learning","author":"R. Munos","year":"2002","unstructured":"Munos, R., Moore, A.: Variable Resolution Discretization in Optimal Control. In: Machine Learning, pp. 291\u2013323. Kluwer Academic Publishers, Dordrecht (2002)"}],"container-title":["Lecture Notes in Computer Science","Bio-Inspired Systems: Computational and Ambient Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-02478-8_73","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T14:06:08Z","timestamp":1558361168000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-02478-8_73"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642024771","9783642024788"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-02478-8_73","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}