Art

J-GLOBAL ID：200902156583005562   Reference number：00A0319995

An Analysis of Actor-Critic Algorithms Using Eligibility Traces. Reinforcement Learning with Imperfect Value Functions.

Actorに適正度の履歴を用いたActor-Criticアルゴリズム 不完全なValue-Functionのもとでの強化学習

Author (2)： KIMURA HAJIME (東京工大 大学院) ,  KOBAYASHI SHIGENOBU (東京工大 大学院)
Material： 人工知能学会誌  (Journal of the Japanese Society for Artificial Intelligence)
Volume： 15  Issue： 2  Page： 267-275  Publication year： Mar. 01, 2000 
JST Material Number： X0330A  ISSN： 0912-8085  Document type： Article
Article type： 原著論文  Country of issue： Japan (JPN)  Language： JAPANESE (JA)

Thesaurus term： *reinforcement learning ,...
Semi thesaurus term： 履歴 ,...

   To see more with JDream III (charged).   {{ this.onShowAbsJLink("http://jdream3.com/lp/jglobal/index.html?docNo=00A0319995&from=J-GLOBAL&jstjournalNo=X0330A") }}

JST classification (1)： Artificial intelligence  (JE08000Z)

Reference (26)：

• C., BAIRD, L. Reinforcement Learning in Continuous Time:Advantage Updating. Proceedings of IEEE International Conference on Neural Networks. 1994, IV, 2448-2453
• BARTO, A. G. Neuronlike Adaptive Elements That Can Solve Difficult Learning Control Problems. IEEE Transactions on Systems, Man, and Cybernetics. 1983, SMC-13, 5, 834-846
• CLOUSE, J. A. A Teaching Method for Reinforcement Learning. Proc.of the 9th International Conference on Machine Learning. 1992, 93-101
• CRITES, R. H. An Actor/Critic Algorithm that is Equivalent to Q-Learning. Advances in Neural Information Processing Systems. 1994, 7, 401-408
• DOYA, K. Efficient Nonlinear Control with Actor-Tutor Architecture. Advances in Neural Information Processing Systems. 1996, 9, 1012-1018

Terms in the title (4)： 履歴 ,  アルゴリズム ,  VALUE ,  強化学習