About J-GLOBAL

日本語

Font size
  • A
  • A

Articleの詳細情報

ArticleJ-GLOBAL ID:200902015659780983整理番号:92A0650620

Existence of Optimal Stationary Policies in Average Reward Markov Decision Processes with a Recurrent State.

再帰状態をもつ平均報酬Markov決定過程における最適定常政策の存在

著者:CAVAZOS‐CADENA R(Univ. Autonoma Agraria Antonio Narro, Saltillo, MEX)
資料名:Appl Math Optim 巻:26 号:2 ページ:171-194
発行年:1992年09月
  • J-GLOBAL home
  • Bookmark J-GLOBAL

J-GLOBAL: Linking, Expanding and Sparking

About J-GLOBAL

Linking

J-GLOBAL links information that represents the key to research and development. For example, linking articles and patents with people (authors and inventors) enables the extraction of a sequence of information.
It’s useful for making new discoveries and uncovering new information.

Expanding

The system enables searches of similar kinds of content through linkage with external sites.
It helps you to obtain knowledge from dissimilar fields and discover concepts that cross the boundaries of specialisms.

Sparking

Through repeated linkage and expansioniteration, J-GLOBAL provides unexpected hints for problem-solving and the illumination of new ideas.