{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T04:05:27Z","timestamp":1745208327168,"version":"3.40.4"},"publisher-location":"Berlin, Heidelberg","reference-count":9,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642344800"},{"type":"electronic","value":"9783642344817"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-34481-7_71","type":"book-chapter","created":{"date-parts":[[2012,11,5]],"date-time":"2012-11-05T08:40:34Z","timestamp":1352104834000},"page":"583-590","source":"Crossref","is-referenced-by-count":1,"title":["Emergence of Multi-step Discrete State Transition through Reinforcement Learning with a Recurrent Neural Network"],"prefix":"10.1007","author":[{"given":"Mohamad Faizal","family":"Samsudin","sequence":"first","affiliation":[]},{"given":"Yoshito","family":"Sawatsubashi","sequence":"additional","affiliation":[]},{"given":"Katsunari","family":"Shibata","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"71_CR1","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":"71_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1007\/978-3-642-03040-6_118","volume-title":"Advances in Neuro-Information Processing","author":"H. Utsunomiya","year":"2009","unstructured":"Utsunomiya, H., Shibata, K.: Contextual Behaviors and Internal Representations Acquired by Reinforcement Learning with a Recurrent Neural Network in a Continuous State and Action Space Task. In: K\u00f6ppen, M., Kasabov, N., Coghill, G. (eds.) ICONIP 2008, Part II. LNCS, vol.\u00a05507, pp. 970\u2013978. Springer, Heidelberg (2009)"},{"key":"71_CR3","doi-asserted-by":"crossref","unstructured":"Shibata, K., Utsunomiya, H.: Discovery of Pattern Meaning from Delayed Rewards by Reinforcement Learning with a Recurrent Neural Network. In: Proc. of Int\u2019l Joint Conf. on Neural Networks 2011, pp. 1445\u20131452, N-0311.pdf (2011)","DOI":"10.1109\/IJCNN.2011.6033394"},{"key":"71_CR4","doi-asserted-by":"crossref","unstructured":"Shibata, K.: Emergence of Intelligence through Reinforcement Learning with a Neural Network. In: Mellouk, A. (ed.) Advances in Reinforcement Learning, pp. 99\u2013120. InTech (2011)","DOI":"10.5772\/13443"},{"key":"71_CR5","unstructured":"Taguchi, Y., Shibata, K.: The Effect of the Initial Weight Values of the Learning Problem that Needs the Internal State Transition by a Recurrent Neural Network. In: Proc. of Kyushu Branch Annual Conf. of SICE, pp. 87\u201390 (2011) (in Japanese)"},{"issue":"5","key":"71_CR6","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":"71_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"},{"key":"71_CR8","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning Internal Representations by Errorpropagating. In: Parallel Distributed Processing, vol.\u00a01, pp. 318\u2013362. MIT Press (1986)","DOI":"10.21236\/ADA164453"},{"key":"71_CR9","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1016\/j.neunet.2004.05.007","volume":"17","author":"J. Tani","year":"2004","unstructured":"Tani, J., Ito, M., Sugita, Y.: Self-organization of Distributedly Represented Multiple Behavior Schemata in a Mirror System: Reviews of Robot Experiments using RNNPB. Neural Networks\u00a017, 1273\u20131289 (2004)","journal-title":"Neural Networks"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-34481-7_71.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,20]],"date-time":"2025-04-20T06:54:15Z","timestamp":1745132055000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-34481-7_71"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642344800","9783642344817"],"references-count":9,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-34481-7_71","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}