{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T06:56:07Z","timestamp":1725605767756},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642215568"},{"type":"electronic","value":"9783642215575"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"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":[[2011]]},"DOI":"10.1007\/978-3-642-21557-5_8","type":"book-chapter","created":{"date-parts":[[2011,9,8]],"date-time":"2011-09-08T15:33:54Z","timestamp":1315496034000},"page":"56-65","source":"Crossref","is-referenced-by-count":9,"title":["Ensemble Methods for Reinforcement Learning with Function Approximation"],"prefix":"10.1007","author":[{"given":"Stefan","family":"Fau\u00dfer","sequence":"first","affiliation":[]},{"given":"Friedhelm","family":"Schwenker","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Baird, L.: Residual Algorithms: Reinforcement Learning with Function Approximation. In: Proceedings of the 12th International Conference on Machine Learning pp. 30\u201337 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"8_CR3","first-page":"123","volume":"24","author":"L. Breiman","year":"1996","unstructured":"Breiman, L.: Bagging Predictors. Machine Learning\u00a024, 123\u2013140 (1996)","journal-title":"Machine Learning"},{"issue":"2","key":"8_CR4","first-page":"197","volume":"5","author":"R.E. Schapire","year":"1990","unstructured":"Schapire, R.E.: The Strength of Learnability. Machine Learning\u00a05(2), 197\u2013227 (1990)","journal-title":"Machine Learning"},{"issue":"4-5","key":"8_CR5","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1016\/S0893-6080(99)00024-6","volume":"12","author":"R. Sun","year":"1999","unstructured":"Sun, R., Peterson, T.: Multi-Agent Reinforcement Learning: Weighting and Partitioning. Journal on Neural Networks\u00a012(4-5), 727\u2013753 (1999)","journal-title":"Journal on Neural Networks"},{"key":"8_CR6","first-page":"1789","volume":"7","author":"J.R. Kok","year":"2006","unstructured":"Kok, J.R., Vlassis, N.: Collaborative Multiagent Reinforcement Learning by Payoff Propagation. Journal of Machine Learning Research\u00a07, 1789\u20131828 (2006)","journal-title":"Journal of Machine Learning Research"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Partalas, I., Feneris, I., Vlahavas, I.: Multi-Agent Reinforcement Learning using Strategies and Voting. In: 19th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2007), vol.\u00a02, pp. 318\u2013324 (2007)","DOI":"10.1109\/ICTAI.2007.15"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Abdallah, S., Lesser, V.: Multiagent Reinforcement Learning and Self-Organization in a Network of Agents. In: Proceedings of the Sixth International Joint Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2007 pp.172\u2013179 (2007)","DOI":"10.1145\/1329125.1329172"},{"key":"8_CR9","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/TSMCB.2008.920231","volume":"38","author":"M.A. Wiering","year":"2008","unstructured":"Wiering, M.A., van Hasselt, H.: Ensemble Algorithms in Reinforcement Learning. IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics\u00a038, 930\u2013936 (2008), ISSN 1083-4419","journal-title":"IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Fau\u00dfer, S., Schwenker, F.: Learning a Strategy with Neural Approximated Temporal-Difference Methods in English Draughts. In: ICPR 2010, pp. 2925\u20132928 (2010)","DOI":"10.1109\/ICPR.2010.717"},{"key":"8_CR11","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","volume-title":"Neural Networks for Pattern Recognition","author":"C.M. Bishop","year":"1995","unstructured":"Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)"},{"key":"8_CR12","volume-title":"Artificial Intelligence: A Modern Approach","year":"2002","unstructured":"Stuart, J.R., Norvig, P.: Artificial Intelligence: A Modern Approach, 2nd edn. Prentice-Hall, Englewood Cliffs (2002)","edition":"2"}],"container-title":["Lecture Notes in Computer Science","Multiple Classifier Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-21557-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T04:39:03Z","timestamp":1712810343000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-21557-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642215568","9783642215575"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-21557-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}