{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T01:31:42Z","timestamp":1772501502279,"version":"3.50.1"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,4]]},"DOI":"10.1109\/adprl.2011.5967372","type":"proceedings-article","created":{"date-parts":[[2011,8,4]],"date-time":"2011-08-04T01:40:00Z","timestamp":1312422000000},"page":"91-96","source":"Crossref","is-referenced-by-count":46,"title":["Reinforcement learning algorithms for solving classification problems"],"prefix":"10.1109","author":[{"given":"Marco A.","family":"Wiering","sequence":"first","affiliation":[]},{"given":"Hado","family":"van Hasselt","sequence":"additional","affiliation":[]},{"given":"Auke-Dirk","family":"Pietersma","sequence":"additional","affiliation":[]},{"given":"Lambert","family":"Schomaker","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref11","author":"hutter","year":"2004","journal-title":"Universal Artificial Intelligence Sequential Decisions Based on Algorithmic Probability"},{"key":"ref12","first-page":"7","article-title":"Universal learning of repeated matrix games","author":"poland","year":"0","journal-title":"Proceedings of the 15th Annual Machine Learning Conference of Belgium and The Netherlands (Benelearn '06)"},{"key":"ref13","first-page":"293","article-title":"Reinforcement learning with self-modifying policies","author":"schmidhuber","year":"1997","journal-title":"Learning to Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007383707642"},{"key":"ref15","first-page":"177","volume":"1","author":"schmidhuber","year":"2009","journal-title":"Ultimate cognition a la Gödel"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920231"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368199"},{"key":"ref18","author":"schmidhuber","year":"1987","journal-title":"Evolutionary principles in self-referential learning or on learning how to learn the meta-meta- … hook Institut für Infor-matik Technische Universität München"},{"key":"ref19","author":"koza","year":"1994","journal-title":"Genetic Programming II Automatic Discovery of Reusable Programs"},{"key":"ref4","first-page":"25","article-title":"Advanced forecasting methods for global crisis warning and models of intelligence","volume":"xxii","author":"werbos","year":"1977","journal-title":"General Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2009.5178745"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2440-0"},{"key":"ref5","first-page":"318","article-title":"Learning internal representations by error propagation","volume":"1","author":"rumelhart","year":"1986","journal-title":"Parallel Distributed Processing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368200"},{"key":"ref7","article-title":"UCI repository of machine learning databases","author":"blake","year":"1998"},{"key":"ref2","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref9","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"}],"event":{"name":"2011 Ieee Symposium On Adaptive Dynamic Programming And Reinforcement Learning","location":"Paris, France","start":{"date-parts":[[2011,4,11]]},"end":{"date-parts":[[2011,4,15]]}},"container-title":["2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5958170\/5967347\/05967372.pdf?arnumber=5967372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,13]],"date-time":"2019-06-13T18:53:18Z","timestamp":1560451998000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5967372\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/adprl.2011.5967372","relation":{},"subject":[],"published":{"date-parts":[[2011,4]]}}}