Markov Decision Processes Discrete Stochastic Dynamic Programming

Name: Markov Decision Processes Discrete Stochastic Dynamic Programming
Price: 80.46 USD
Availability: InStock
ISBN: 9780471727828

ISBN-10: 0471727822

ISBN-13: 9780471727828

Edition: 2nd 1994

Authors: Martin L. Puterman

List price: $167.95

This item qualifies for FREE shipping.

30 day, 100% satisfaction guarantee!

Sell

Get cash fast!

Buy new: $130.70

Marketplace

3 new & used from $80.46

what's this?

Rush Rewards U
Members Receive:

You have reached 400 XP and carrot coins. That is the daily max!

An up-to-date, unified and rigorous treatment of theoretical, computational and applied research on Markov decision process models. Concentrates on infinite-horizon discrete-time models. Discusses arbitrary state spaces, finite-horizon and continuous-time discrete-state models. Also covers modified policy iteration, multichain models with average reward criterion and sensitive optimality. Features a wealth of figures which illustrate examples and an extensive bibliography.

Book details

List price: $167.95
Edition: 2nd
Copyright year: 1994
Publisher: John Wiley & Sons, Incorporated
Publication date: 3/3/2005
Binding: Paperback
Pages: 684
Size: 6.10" wide x 9.20" long x 1.40" tall
Weight: 2.398

Martin L. Puterman, PhD, is Advisory Board Professor of Operations and Director of the Centre for Operations Excellence at The University of British Columbia in Vancouver, Canada.



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