{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T15:00:23Z","timestamp":1759935623578},"reference-count":21,"publisher":"Informa UK Limited","issue":"7-8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Artificial Intelligence"],"published-print":{"date-parts":[[2008,8,26]]},"DOI":"10.1080\/08839510802170538","type":"journal-article","created":{"date-parts":[[2008,8,19]],"date-time":"2008-08-19T23:44:42Z","timestamp":1219189482000},"page":"761-779","source":"Crossref","is-referenced-by-count":14,"title":["REINFORCEMENT LEARNING FOR POMDP USING STATE CLASSIFICATION"],"prefix":"10.1080","volume":"22","author":[{"given":"Le Tien","family":"Dung","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Komeda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Motoki","family":"Takagi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","reference":[{"key":"CIT0001","first-page":"1475","volume":"14","author":"Bakker B.","year":"2002","journal-title":"Advances in Neural Information Processing Systems"},{"key":"CIT0004","volume-title":"Reinforcement Learning","author":"Champandard A. J."},{"key":"CIT0005","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"CIT0006","doi-asserted-by":"publisher","DOI":"10.1162\/153244303768966139"},{"key":"CIT0007","doi-asserted-by":"crossref","unstructured":"Gomez , F. and J. Schmidhuber . ( 2005 ). Co-evolving recurrent neurons learn deep memory POMDPs. InProceedings of the Conference on Genetic and Evolutionary Computation, GECCO-05, Washington , DC , 1795 \u2013 1802 .","DOI":"10.1145\/1068009.1068092"},{"key":"CIT0008","doi-asserted-by":"crossref","unstructured":"Gomez , F. , J. Schmidhuber , and R. Miikkulainen . ( 2006 ). Efficient non-linear control through neuroevolution. InProceedings of the European Conference on Machine Learning, ECML-06, Berlin .","DOI":"10.1007\/11871842_64"},{"key":"CIT0009","first-page":"437","volume":"1","author":"Ho F.","year":"1994","journal-title":"IEEE World Congress on Computational Intelligence, Proceedings of the ICNN"},{"key":"CIT0010","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"CIT0011","volume-title":"Advances in Neural Information Processing Systems","author":"Jaakkola T.","year":"1995"},{"key":"CIT0012","author":"Kaelbling L. P.","year":"1996","journal-title":"Journal of Artificial Intelligence Research."},{"key":"CIT0013","volume-title":"Reinforcement Learning for Robots Using Neural Networks","author":"Lin L.-J.","year":"1993"},{"key":"CIT0014","volume-title":"Proceedings of the 2nd International Conference on Simulation of Adaptive behavior","author":"Lin L.-J.","year":"1993"},{"key":"CIT0016","first-page":"387","volume-title":"Proceedings of the 12th International Conference Machine Learning","author":"McCallum R. A.","year":"1995"},{"key":"CIT0017","first-page":"377","author":"McCallum R. A.","year":"1995","journal-title":"Advances in Neural Information Processing Systems"},{"key":"CIT0020","unstructured":"Samuel , B. , and W. Hasinoff . ( 2002 ). Reinforcement learning for problems with hidden state. Tech. Report , University of Toronto ."},{"key":"CIT0021","unstructured":"Schafer , A. M. , and S. Udluft . ( 2005 ). Solving partially observable reinforcement learning problems with recurrent neural networks. InProceedings of the 16th European Conference on Machine Learning, ECML-05, Porto , Portugal ."},{"key":"CIT0022","first-page":"500","volume":"3","author":"Schmidhuber J. H.","year":"1991","journal-title":"Advances in Neural Information Processing Systems"},{"key":"CIT0023","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2007.19.3.757"},{"key":"CIT0024","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R.","year":"1998"},{"key":"CIT0025","volume-title":"Learning from Delayed Rewards","author":"Watkins C. J. C. H.","year":"1989"},{"key":"CIT0026","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00012-P"}],"container-title":["Applied Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/08839510802170538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,13]],"date-time":"2019-05-13T12:48:42Z","timestamp":1557751722000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.tandfonline.com\/doi\/abs\/10.1080\/08839510802170538"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,8,26]]},"references-count":21,"journal-issue":{"issue":"7-8","published-print":{"date-parts":[[2008,8,26]]}},"alternative-id":["10.1080\/08839510802170538"],"URL":"https:\/\/doi.org\/10.1080\/08839510802170538","relation":{},"ISSN":["0883-9514","1087-6545"],"issn-type":[{"value":"0883-9514","type":"print"},{"value":"1087-6545","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,8,26]]}}}