Art

J-GLOBAL ID：200902132218151359   Reference number：99A0929219

Adaptive internal state space construction method for reinforcement learning of a real-world agent.

実世界エージェントの強化学習の適応内部状態空間構成

Author (2)： SAMEJIMA K (Tokyo Univ. Agriculture and Technol., Tokyo, JPN) ,  OMORI T (Tokyo Univ. Agriculture and Technol., Tokyo, JPN)
Material： Neural Networks  (Neural Netw)
Volume： 12  Issue： 7/8  Page： 1143-1155  Publication year： Oct. 1999 
JST Material Number： T0698A  ISSN： 0893-6080  Document type： Article
Article type： 原著論文  Country of issue： United Kingdom (GBR)  Language： ENGLISH (EN)

Thesaurus term： *reinforcement learning ,...
Semi thesaurus term： navigation(robot)

   To see more with JDream III (charged).   {{ this.onShowAbsJLink("http://jdream3.com/lp/jglobal/index.html?docNo=99A0929219&from=J-GLOBAL&jstjournalNo=T0698A") }}

JST classification (2)： Artificial intelligence  (JE08000Z) ,  Motion and control of robots  (IC04012J)

Reference (18)：

• ANDERSON, C. W. Q-learning with hidden-unit restarting, Advances in neural information processing system 5. 1993, 81-88
• ASADA, M. Behavior acquisition via vision-based robot learning. Rbotics Research : the Seventh International Symposium. 1996, 279-286
• ATKESON, C. G. Locally weighted learning. Artificial Intelligence Review. 1997, 11, 11-73
• BARTO, A. G. Neuronlike adaptive element that can solve difficult learning control problem. IEEE Transaction on System, Man, and Cybernetics. 1983, 13, 834-846
• BOYAN, J. A. Generalization in reinforcement learning : safety approximation the value function, Advances in neural information processing sy. 1994, 369-376

Terms in the title (6)： 世界 ,  エージェント ,  強化学習 ,  適応 ,  内部状態 ,  空間構成