{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T12:09:14Z","timestamp":1725538154967},"publisher-location":"Berlin, Heidelberg","reference-count":9,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642318368"},{"type":"electronic","value":"9783642318375"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-31837-5_12","type":"book-chapter","created":{"date-parts":[[2012,7,5]],"date-time":"2012-07-05T02:48:56Z","timestamp":1341456536000},"page":"80-86","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcement Learning Based on Extreme Learning Machine"],"prefix":"10.1007","author":[{"given":"Jie","family":"Pan","sequence":"first","affiliation":[]},{"given":"Xuesong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Ge","family":"Cao","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"issue":"9","key":"12_CR2","first-page":"680","volume":"41","author":"K. Abe","year":"2002","unstructured":"Abe, K.: Reinforcement Learning-Value Function Estimation and Policy Search. Society of Instrument and Control Engineers\u00a041(9), 680\u2013685 (2002)","journal-title":"Society of Instrument and Control Engineers"},{"issue":"7\/8","key":"12_CR3","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.1166\/jctn.2007.013","volume":"4","author":"X.S. Wang","year":"2007","unstructured":"Wang, X.S., Tian, X.L., Cheng, Y.H.: Value Approximation with Least Squares Support Vector Machine in Reinforcement Learning System. Journal of Computational and Theoretical Nanoscience\u00a04(7\/8), 1290\u20131294 (2007)","journal-title":"Journal of Computational and Theoretical Nanoscience"},{"issue":"9","key":"12_CR4","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1016\/j.ins.2011.01.001","volume":"181","author":"N.A. Vien","year":"2011","unstructured":"Vien, N.A., Yu, H., Chung, T.C.: Hessian Matrix Distribution for Bayesian Policy Gradient Reinforcement Learning. Information Sciences\u00a0181(9), 1671\u20131685 (2011)","journal-title":"Information Sciences"},{"key":"12_CR5","first-page":"25","volume-title":"Proceedings of the International Joint Conference on Neural Networks","author":"G.B. Huang","year":"2004","unstructured":"Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme Learning Machine: A New Learning Scheme of Feedforward Neural Networks. In: Proceedings of the International Joint Conference on Neural Networks, pp. 25\u201329. The MIT Press, Budapest (2004)"},{"key":"12_CR6","first-page":"2425","volume-title":"Proceedings of the 29th Chinese Control Conference","author":"S. Ding","year":"2010","unstructured":"Ding, S., Su, C.Y.: Application of Optimizing Bp Neural Networks Algorithm Based on Genetic Algorithm. In: Proceedings of the 29th Chinese Control Conference, pp. 2425\u20132428. The MIT Press, Beijing (2010)"},{"key":"12_CR7","first-page":"54","volume-title":"Proceedings of the International Conference on Advanced Computer Theory and Engineering","author":"G. Wang","year":"2010","unstructured":"Wang, G., Li, P.: Dynamic Adaboost Ensemble Extreme Learning Machine. In: Proceedings of the International Conference on Advanced Computer Theory and Engineering, pp. 54\u201358. The MIT Press, Chengdu (2010)"},{"issue":"3","key":"12_CR8","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1109\/5326.704563","volume":"28","author":"L. Jouffe","year":"1998","unstructured":"Jouffe, L.: Fuzzy Inference System Learning By Reinforcement Methods. IEEE Transactions on Systems, Man and Cybernetics\u00a028(3), 338\u2013355 (1998)","journal-title":"IEEE Transactions on Systems, Man and Cybernetics"},{"key":"12_CR9","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1109\/CDC.1997.650692","volume-title":"Proceedings of the IEEE Conference on Decision and Control","author":"A. Thomas","year":"1997","unstructured":"Thomas, A., Marcus, S.I.: Reinforcement Learning for MDPs Using Temporal Difference Schemes. In: Proceedings of the IEEE Conference on Decision and Control, pp. 577\u2013583. The MIT Press, San Diego (1997)"}],"container-title":["Communications in Computer and Information Science","Emerging Intelligent Computing Technology and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-31837-5_12.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T11:48:53Z","timestamp":1620128933000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-31837-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642318368","9783642318375"],"references-count":9,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-31837-5_12","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2012]]}}}