{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T18:59:47Z","timestamp":1725562787744},"publisher-location":"Berlin, Heidelberg","reference-count":5,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642158216"},{"type":"electronic","value":"9783642158223"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-15822-3_29","type":"book-chapter","created":{"date-parts":[[2010,8,12]],"date-time":"2010-08-12T11:21:34Z","timestamp":1281612094000},"page":"222-227","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning Based Neural Controllers for Dynamic Processes without Exploration"],"prefix":"10.1007","author":[{"given":"Frank-Florian","family":"Steege","sequence":"first","affiliation":[]},{"given":"Andr\u00e9","family":"Hartmann","sequence":"additional","affiliation":[]},{"given":"Erik","family":"Schaffernicht","sequence":"additional","affiliation":[]},{"given":"Horst-Michael","family":"Gross","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"unstructured":"Watkins, C.: Learning from delayed rewards, PhD Thesis, University of Cambridge, England (1989)","key":"29_CR1"},{"key":"29_CR2","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/11564096_32","volume-title":"Machine Learning: ECML 2005","author":"M. Riedmiller","year":"2005","unstructured":"Riedmiller, M.: Neural fitted Q-Iteration - First Experiences with a Data Efficient Neural Reinforcement Learning Method. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L. (eds.) ECML 2005. LNCS (LNAI), vol.\u00a03720, pp. 317\u2013328. Springer, Heidelberg (2005)"},{"doi-asserted-by":"crossref","unstructured":"Riedmiller, M.: Neural Reinforcement Learning to Swing-Up and Balance a Real Pole. In: Proc. Int. Conf. SMC, vol.\u00a04, pp. 3191\u20133196 (2005)","key":"29_CR3","DOI":"10.1109\/ICSMC.2005.1571637"},{"unstructured":"Price, B., Boutilier, C.: A Bayesian Approach to Imitation in Reinforcement Learning. In: Proc. IJCAI, pp. 712\u2013720 (2003)","key":"29_CR4"},{"key":"29_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/978-3-642-04617-9_50","volume-title":"KI 2009: Advances in Artificial Intelligence","author":"E. Schaffernicht","year":"2009","unstructured":"Schaffernicht, E., Stephan, V., Debes, K., Gross, H.-M.: Machine Learning Techniques for Selforganizing Combustion Control. In: Mertsching, B., Hund, M., Aziz, Z. (eds.) KI 2009. LNCS, vol.\u00a05803, pp. 395\u2013402. Springer, Heidelberg (2009)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks \u2013 ICANN 2010"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-15822-3_29.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T02:41:02Z","timestamp":1606185662000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-15822-3_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642158216","9783642158223"],"references-count":5,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-15822-3_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}