Art

J-GLOBAL ID：200902112711295156   Reference number：97A1015777

Reinforcement Learning. Reinforcement Learning Systems for Discrete Markov Decision Processes.

強化学習 離散マルコフ決定過程下での強化学習

Author (2)： MIYAZAKI KAZUMITSU (東京工大 大学院 総合理工学研究科) ,  KOBAYASHI SHIGENOBU (東京工大 大学院 総合理工学研究科)
Material： 人工知能学会誌  (Journal of the Japanese Society for Artificial Intelligence)
Volume： 12  Issue： 6  Page： 811-821  Publication year： Nov. 1997 
JST Material Number： X0330A  ISSN： 0912-8085  Document type： Article
Article type： 解説  Country of issue： Japan (JPN)  Language： JAPANESE (JA)

Thesaurus term： *Markov process ,...
Semi thesaurus term： 報酬獲得 ,...

   To see more with JDream III (charged).   {{ this.onShowAbsJLink("http://jdream3.com/lp/jglobal/index.html?docNo=97A1015777&from=J-GLOBAL&jstjournalNo=X0330A") }}

JST classification (2)： System and control theory in general  (IA02010H) ,  Artificial intelligence  (JE08000Z)

Reference (29)：

• BASYE, K. Learning dynamics: system identification for perceptually challenged agents. Artificial Intelligence. 1995, 72, 139-171
• BRADTKE, S. J. Reinforcement Learning Method for Continuous-Time Markov Decision Problems. Advances in Neural Information Processing Systems. 1994, 7, 393-400
• CLOUSE, J. A. Teaching Method for Reinforcement Learning. Proc. of 9th International Conference on Machine Learning. 1992, 92-101
• DAYAN, P. The convergence of TD (λ) for general λ. Machine Learning. 1992, 8, 341-362
• DEAN, T. Inferring Finite Automata with Stochastic Output Function and an Application to Map Learning. Proc. of 10th National Conference on Artificial Intelligence. 1992, 208-214

Terms in the title (2)： 強化学習 ,  マルコフ決定過程