Art

J-GLOBAL ID：201202223870981259   Reference number：12A1698206

Performance Improvement by Identification-based XCS Using Predicted Reward

予測報酬に基づく個別化による学習分類子システムの学習性能の向上

Author (5)： NAKATA MASAYA (電通大) ,  HARADA TOMOHIRO (電通大) ,  SATO KEIJI (電通大) ,  MATSUSHIMA HIROYASU (電通大) ,  TAKADAMA KEIKI (電通大)
Material： 計測自動制御学会論文集  (Transactions of the Society of Instrument and Control Engineers)
Volume： 48  Issue： 11  Page： 713-722  Publication year： Nov. 30, 2012 
JST Material Number： S0104A  ISSN： 0453-4654  CODEN： KJSRA  Document type： Article
Article type： 原著論文  Country of issue： Japan (JPN)  Language： JAPANESE (JA)

Thesaurus term： *learning algorithm ,  *adaptive system ,  computer algorithm ,  forecast ,  *evolution algorithm
Semi thesaurus term： *evolution algorithm ,  *classification algorithm ,  *reward prediction

JST classification (1)： Artificial intelligence  (JE08000Z)

Reference (14)：

• HOLLAND, J. H. Escaping Brittleness : The Possibilities of General Purpose Learning Algorithms Applied to Parallel Rule-based System. Machine Learning. 1986, 2, 593-623
• WATKINS, J. C. J. Learning from Delayed Rewards. Ph.D. thesis, Cambridge University. 1989
• SUTTON, R. S. Learning to Predict by the Methods of Temporal Differences. Machine Learning. 1988, 3, 9-14
• GOLDBERG, D. E. Genetic Algorithms in Search, Optimization, and Machine Learning. 1989
• WILSON, S. W. Classifier fitness based on accuracy. Evolutionary Computation. 1995, 3, 2, 149-175

Terms in the title (4)： 予測 ,  報酬 ,  学習分類子システム ,  学習性能