Art

J-GLOBAL ID：200902176508281849   Reference number：00A0935561

Convergence of the Q-ae Learning on Deterministic MDPs and Its Efficiency on the Stochastic Environment.

確定的Markov決定過程上のQ-ae学習の収束と確率的環境におけるその効率

Author (3)： ZHAO G (Osaka City Univ., Osaka-shi, JPN) ,  TATSUMI S (Osaka City Univ., Osaka-shi, JPN) ,  SUN R (Liaoning Univ., Shenyang-shi, CHN)
Material： IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences (Institute of Electronics, Information and Communication Engineers)  (IEICE Trans Fundam Electron Commun Comput Sci (Inst Electron Inf Commun Eng))
Volume： E83-A  Issue： 9  Page： 1786-1795  Publication year： Sep. 25, 2000 
JST Material Number： F0699C  ISSN： 0916-8508  Document type： Article
Article type： 原著論文  Country of issue： Japan (JPN)  Language： ENGLISH (EN)

Thesaurus term： *reinforcement learning ,...

   To see more with JDream III (charged).   {{ this.onShowAbsJLink("http://jdream3.com/lp/jglobal/index.html?docNo=00A0935561&from=J-GLOBAL&jstjournalNo=F0699C") }}

JST classification (1)： Artificial intelligence  (JE08000Z)

Reference (21)：

• BERTSEKAS, D. P. Dynamic programming and stochastic control. Mathematics in Science and Engineering. 1976, 125
• GREFENSTETTE, J. J. Credit assignment in rule discovery systems based on genetic algorithms. Machine Learning. 1988, 3, 225-245
• HOWARD, R. A. Dynamic programming and Markov processes. 1960
• JAAKKOLA, T. On the convergence of stochastic iterative dynamic programming algorithms. Neural Computation. 1994, 6, 6, 1185-1201
• KAELBLING, L. P. An adaptable mobile robot. Proc. 1st European Conf. on Artificial Life. 1991, 41-47

Terms in the title (7)： 確定 ,  Markov決定過程 ,  AE ,  学習 ,  収束 ,  確率 ,  環境