{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T16:40:03Z","timestamp":1739292003864,"version":"3.37.0"},"publisher-location":"Berlin, Heidelberg","reference-count":9,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642030390"},{"type":"electronic","value":"9783642030406"}],"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\/978-3-642-03040-6_118","type":"book-chapter","created":{"date-parts":[[2009,7,30]],"date-time":"2009-07-30T12:16:37Z","timestamp":1248956197000},"page":"970-978","source":"Crossref","is-referenced-by-count":8,"title":["Contextual Behaviors and Internal Representations Acquired by Reinforcement Learning with a Recurrent Neural Network in a Continuous State and Action Space Task"],"prefix":"10.1007","author":[{"given":"Hiroki","family":"Utsunomiya","sequence":"first","affiliation":[]},{"given":"Katsunari","family":"Shibata","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"118_CR1","unstructured":"Lin, L., Mitchell, T.M.: Memory Approaches to Reinforcement Learning In Non-Markovian Domains. Technical Report CMU-CS-TR-92-138, CMU, Computer Science (1992)"},{"key":"118_CR2","doi-asserted-by":"crossref","unstructured":"Onat, A., Kita, H., Nishikawa, Y.: Recurrent Neural Networks for Reinforcement Learning: Architecture, Learning Algorithms and Internal Representation. In: Proc. of IJCNN 1998, pp. 2010\u20132015 (1998)","DOI":"10.1109\/IJCNN.1998.687168"},{"key":"118_CR3","doi-asserted-by":"crossref","unstructured":"Mizutani, E., Dreyfus, S.E.: Totally Model-Free Reinforcement Learning by Actor-Critic Elman Network in Non-Markovian Domains. In: Proc. of IJCNN 1998, pp. 2016\u20132021 (1998)","DOI":"10.1109\/IJCNN.1998.687169"},{"key":"118_CR4","unstructured":"Onat, A., Kita, H., Nishikawa, Y.: Q-Learning with Recurrent Neural Networks as a Controller for the Inverted Pendulum Problem. In: Proc. of ICONIP 1998, pp. 837\u2013840 (1998)"},{"key":"118_CR5","doi-asserted-by":"crossref","unstructured":"Bakker, B., Linaker, F., Schmidhuber, J.: Reinforcement Learning in Partially Observable Mobile Robot Domains Using Unsupervised Event Extraction. In: Proc. of IROS 2002, vol.\u00a01, pp. 938\u2013943 (2002)","DOI":"10.1109\/IRDS.2002.1041511"},{"key":"118_CR6","doi-asserted-by":"crossref","unstructured":"Bakker, B., Zhumatiy, V., Gruener, G., Schmidhuber, J.: A Robot that Reinforcement-Learns to Identify and Memorize Important Previous Observations. In: Proc. of IROS 2003, pp. 430\u2013435 (2003)","DOI":"10.1109\/IROS.2003.1250667"},{"key":"118_CR7","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","volume":"14","author":"J.L. Elman","year":"1990","unstructured":"Elman, J.L.: Finding structure in time. Cognitive Science\u00a014, 179\u2013211 (1990)","journal-title":"Cognitive Science"},{"issue":"5","key":"118_CR8","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","volume":"13","author":"A.G. Barto","year":"1983","unstructured":"Barto, A.G., Sutton, R.S., Anderson, W.: Neuronlike adaptive elements can solve difficult learning control problems. IEEE Trans. on Systems, Man, and Cybernetics\u00a013(5), 834\u2013846 (1983)","journal-title":"IEEE Trans. on Systems, Man, and Cybernetics"},{"key":"118_CR9","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/5236.001.0001","volume-title":"Parallel distributed processing","author":"D.E. Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., McClelland, J.L., Group, P.R. (eds.) Parallel distributed processing. MIT Press, Cambridge (1986)"}],"container-title":["Lecture Notes in Computer Science","Advances in Neuro-Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-03040-6_118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T15:29:08Z","timestamp":1739287748000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-03040-6_118"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642030390","9783642030406"],"references-count":9,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-03040-6_118","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}