{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T16:47:57Z","timestamp":1725900477629},"publisher-location":"Berlin\/Heidelberg","reference-count":7,"publisher":"Springer-Verlag","isbn-type":[{"type":"print","value":"3540250565"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/3-540-32392-9_57","type":"book-chapter","created":{"date-parts":[[2006,5,27]],"date-time":"2006-05-27T07:09:20Z","timestamp":1148713760000},"page":"481-485","source":"Crossref","is-referenced-by-count":0,"title":["A New Programming Interface for Reinforcement Learning Simulations"],"prefix":"10.1007","author":[{"given":"Gabriela","family":"\u015eerban","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"57_CR1","volume-title":"Machine Learning","author":"F. Bergadano","year":"1991","unstructured":"Bergadano, F., Giordana, A. (1991) Machine Learning. Ellis Horwood Limited, Chichester, England"},{"key":"57_CR2","doi-asserted-by":"crossref","unstructured":"Fiechter, C.N. (1994) Efficient Reinforcement Learning. Proceedings of the 7th annual ACM Conference on Computer Learning theory, 88\u201397","DOI":"10.1145\/180139.181019"},{"key":"57_CR3","unstructured":"Harmon, M., Harmon, S. (2000) Reinforcement Learning-A Tutorial. Wright State University, www-anw.cs.umass.edu\/mharmon\/rltutorial\/frames. html"},{"issue":"2","key":"57_CR4","first-page":"9","volume":"XLVI","author":"G. Serban","year":"2001","unstructured":"Serban, G. (2001) A Reinforcement Learning Intelligent Agent. Studia Universitatis \u201cBabes-Bolyai\u201d, Informatica XLVI(2), 9\u201318","journal-title":"Studia Universitatis \u201cBabes-Bolyai\u201d, Informatica"},{"key":"57_CR5","unstructured":"Serban, G. (2001) Training Hidden Markov Models-a Method for Training Intelligent Agents. Proceedings of the Second International Workshop of Central and Eastern Europe on Multi-Agent Systems, Krakow, Poland, 267\u2013276"},{"issue":"1","key":"57_CR6","first-page":"3","volume":"XLVIII","author":"G. Serban","year":"2003","unstructured":"Serban, G. (2003) A New Reinforcement Learning Algorithm. Studia Universitatis \u201cBabes-Bolyai\u201d, Informatica XLVIII(1), 3\u201314","journal-title":"Studia Universitatis \u201cBabes-Bolyai\u201d, Informatica"},{"key":"57_CR7","volume-title":"Reinforcement learning","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A., G. (1998) Reinforcement learning. The MIT Press, Cambridge, England"}],"container-title":["Advances in Soft Computing","Intelligent Information Processing and Web Mining"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-32392-9_57.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,28]],"date-time":"2021-04-28T00:54:00Z","timestamp":1619571240000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-32392-9_57"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["3540250565"],"references-count":7,"URL":"https:\/\/doi.org\/10.1007\/3-540-32392-9_57","relation":{},"subject":[]}}