Art

J-GLOBAL ID：200902168136770888   Reference number：96A0772764

Reinforcement Learning in Partially Observable Markov Decision Processes: A Stochastic Gradient Method.

部分観測マルコフ決定過程下での強化学習: 確率的傾斜法による接近

Author (3)： KIMURA HAJIME (東京工大 大学院) ,  YAMAMURA MASAYUKI (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： 11  Issue： 5  Page： 761-768  Publication year： Sep. 1996 
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： learning ,...

   To see more with JDream III (charged).   {{ this.onShowAbsJLink("http://jdream3.com/lp/jglobal/index.html?docNo=96A0772764&from=J-GLOBAL&jstjournalNo=X0330A") }}

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

Reference (13)：

• CHRISMAN, L. Reinforcement learning with Perceptual aliasing : The perceptual Distinctions Approach. Proc. 10th Nat. Conf. on Artificial Intelligence. 1992, 183-188
• JAAKKOLA, T. Reinforcement Learning Algorithm for Partially Observable Markov Decision Problems. Advances in Neural Information Processing Systems. 1994, 345-352
• KIMURA, H. Reinforcement Learning by Stochastic Hill Climbing on Discounted Reward. Proc. 12th Int. Conf. on Machine Learning. 1995, 295-303
• LITTMAN, M. L. Learning policies for partially observable environments : Scaling up. Proc. 12th Int. Conf. on Machine Learning. 1995, 362-370
• McCALLUM, R. A. Instance-Based Utile Distinctions for Reinforcement Learning with Hidden State. Proc. 12th Int. Conf. on Machine Learning. 1995, 387-395

Terms in the title (5)： 部分観測マルコフ決定過程 ,  強化学習 ,  確率 ,  傾斜法 ,  接近