Art

J-GLOBAL ID：200902296121222335   Reference number：08A0318469

Reinforcement Learning with Orthonormal Basis Adaptation Based on Activity-Oriented Index Allocation

活性指向指数割当てに基づく正規直交基底適応による強化学習

Author (1)： SATOH Hideki (Future Univ.-Hakodate, Hakodate-shi, JPN)
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： E91-A  Issue： 4  Page： 1169-1176  Publication year： Apr. 01, 2008 
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 ,  function approximation ,  canonical formalism ,  orthogonality ,  approximation method ,  logistic map ,  suppression and control ,  chaos ,  *nonlinear problem ,  improvement ,  redundancy(property) ,  noise elimination ,  higher dimension ,  basis set ,  activity(property) ,  adaptive control ,  performance evaluation ,  robustness ,  algorithm ,  displacement(replacement)
Semi thesaurus term： linear approximation ,  chaos control ,  performance improvement ,  multi-dimension

JST classification (2)： System design and analysis  (IA02030D) ,  Artificial intelligence  (JE08000Z)

Reference (15)：

• SUTTON, R. S. Reinforcement Learning. 1998
• BAIRD, L. C. Reinforcement learning with high-dimensional, continuous actions. 1993
• UTHER, W. T. B. Tree based discretization for continuous state space reinforcement learning. Proc. AAAI-98, July. 1998, 769-774
• SAMEJIMA, K. Adaptive internal state space construction method for reinforcement learning of a real-world agent. Neural Netw. 1999, 12, 7-8, 1143-1155
• MENACHE, I. Basis function adaptation in temporal difference reinforcement learning. Annals of Operations Research. 2005, 134, 1, 215-238

Terms in the title (5)： 活性 ,  割当て ,  基底 ,  適応 ,  強化学習