Welcome to Education by Design's Online store. We have brought to you a selection of products like Books : Markov Decision Processes. Discrete Stochastic Dynamic Programming Wiley Series in Probability and Statistics along with it's reviews, pictures and related products. All sales from these pages goes towards the creation and maintenance of our educational online activities, articles and resources. We have over 40,000 online stories submitted by kids around the world.

Markov Decision Processes. Discrete Stochastic Dynamic Programming Wiley Series in Probability and Statistics

Normal Price:$111.50
Our Price:$94.50
Availability:Usually ships in 24 hours

... For more information or Buy from Amazon.com ...

Manufacturer: Wiley-Interscience
Author: Martin L. Puterman
Binding: Paperback
Publication Date: 2005-03-03
Publisher: Wiley-Interscience
Label: Wiley-Interscience
Number Of Pages: 680

NEW!!

Enjoy drawing this product with our drawing board.

Drawing Activity for this product

Features for Markov Decision Processes. Discrete Stochastic Dynamic Programming Wiley Series in Probability and Statistics :

Small Picture
Medium Picture

Editorial Review
The Wiley-Interscience Paperback Series consists of selected books that have been made more accessible to consumers in an effort to increase global appeal and general circulation. With these new unabridged softcover volumes, Wiley hopes to extend the lives of these works by making them available to future generations of statisticians, mathematicians, and scientists.
"This text is unique in bringing together so many results hitherto found only in part in other texts and papers. . . . The text is fairly self-contained, inclusive of some basic mathematical results needed, and provides a rich diet of examples, applications, and exercises. The bibliographical material at the end of each chapter is excellent, not only from a historical perspective, but because it is valuable for researchers in acquiring a good perspective of the MDP research potential."
-Zentralblatt fur Mathematik
". . . it is of great value to advanced-level students, researchers, and professional practitioners of this field to have now a complete volume (with more than 600 pages) devoted to this topic. . . . Markov Decision Processes: Discrete Stochastic Dynamic Programming represents an up-to-date, unified, and rigorous treatment of theoretical and computational aspects of discrete-time Markov decision processes."
-Journal of the American Statistical Association
Cached date: AWS Called=true

Customer Reviews

From the author of Approximate Dynamic Programming

2007-12-15
For anyone looking for an introduction to classic discrete state, discrete action Markov decision processes this is the last in a long line of books on this theory, and the only book you will need. The presentation covers this elegant theory very thoroughly, including all the major problem classes (finite and infinite horizon, discounted reward, average reward). The presentation is rigorous, and while it will be best appreciated by doctoral students and the research community, most of the presentation can be easily understood by a masters audience with a strong background in probability.

Discrete state, discrete action models have seen limited applications because of the well-known "curse of dimensionality." This field has perhaps been best known for its ability to identify theoretical properties of models and algorithms (the book has a nice presentation of monotone policies, for example). Practical algorithms for dynamic programs typically require the approximation techniques that have evolved under names such as neuro-dynamic programming (Neuro-Dynamic Programming (Optimization and Neural Computation Series, 3)), reinforcement learning (Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning)), or approximate dynamic programming (Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics)).

Warren B. Powell
Professor
Princeton University

Excellent and detailed, although focusing on exact algorithms only

2007-06-04
Anyone working with Markov Decision Processes should have this book. It has detailed explanations of several algorithms for MDPs: linear programming, value iteration and policy iteration for finite and infinite horizon; total-reward and average reward criteria, and there's one last chapter on continuous-time MDPs (SMDPs).

However, it does not cover some new ideas like partitioning and some faster approximated algorithms. But still, it is a great book!

Make sure to also get Bertsekas' "Dynamic Programming and Optimal Control".