Markov decision processes : discrete stochastic dynamic programming
著者
書誌事項
Markov decision processes : discrete stochastic dynamic programming
（Wiley series in probability and mathematical statistics, . Applied probability and statistics）
Wiley, c1994
大学図書館所蔵 件 / 全65件
-
該当する所蔵館はありません
- すべての絞り込み条件を解除する
この図書・雑誌をさがす
注記
"A Wiley-Interscience publication"
Bibliography: p. 613-642
Includes index
内容説明・目次
内容説明
A Markov chain is a sequence of events where the probability of each event is dependent on the event immediately preceding it, but independent of earlier events. Models and numerical equations are used to describe the patterns. This process is particularly useful in operations research and decision science for plotting the sequence of actions which will cause a system to perform optimally. This study provides a unified treatment of the theory, applications and computational methods for Markov decision processes. Important topics featured include action elimination methods, value iteration in the average reward case and sensitive discount optimality.
目次
Model Formulation. Examples. Finite--Horizon Markov Decision Processes. Infinite--Horizon Models: Foundations. Discounted Markov Decision Problems. The Expected Total--Reward Criterion. Average Reward and Related Criteria. The Average Reward Criterion--Multichain and Communicating Models. Sensitive Discount Optimality. Continuous--Time Models. Afterword. Notation. Appendices. Bibliography. Index.
「Nielsen BookData」 より