Markov Decision Processes (MDPs) are a mathematical framework for modeling sequential decision problems under uncertainty as well as Reinforcement Learning problems. Written by experts in the field, this book provides a global view of current research using MDPs in Artificial Intelligence. It starts with an introductory presentation of the fundamental aspects of MDPs (planning in MDPs, Reinforcement Learning, Partially Observable MDPs, Markov games and the use of non-classical criteria). Then it presents more advanced research trends in the domain and gives some concrete examples using illustrative applications.This book presents a decision problem type commonly called sequential decision problems under uncertainty. The first feature of such problems resides in the relation between the current decision and future decisions. ... The second characteristic of the problems discussed in these pages is the uncertainty in the consequences of all available decisions (actions). ... an agent wishes to decide which is its best strategy (do nothing, replace parts preventively, repair, change car, etc.)anbsp;...
|Title||:||Markov Decision Processes in Artificial Intelligence|
|Author||:||Olivier Sigaud, Olivier Buffet|
|Publisher||:||John Wiley & Sons - 2013-03-04|