The logic of adaptive behavior knowledge representation and algorithms for adaptive sequential decision making under uncertainty in first-order and relational domains /

Markov decision processes have become the de facto standard in modeling and solving sequential decision making problems under uncertainty. This book studies lifting Markov decision processes, reinforcement learning and dynamic programming to the first-order (or, relational) setting.

Bibliographic Details
Main Author: Otterlo, Martijn van.
Corporate Author: IOS Press.
Format: Electronic
Language:English
Published: Amsterdam ; Washington, D.C. : Ios Press, c2009.
Series:Frontiers in artificial intelligence and applications ; v. 192.
Subjects:
Online Access:ebrary
View fulltext via EzAccess
An electronic book accessible through the World Wide Web; click for information
https://ezaccess.library.uitm.edu.my/login?url=http://swb.eblib.com/patron/FullRecord.aspx?p=448789
Table of Contents:
  • Title page; Preface; Contents; CHAPTER 1. Introduction; 1.1. Science and Engineering of Adaptive Behavior; 1.2. You Can Only Learn What You Can Represent; 1.3. About the Contents and Structure of this Book; PART I. Learning Sequential Decision Making under Uncertainty; CHAPTER 2. Markov Decision Processes: Concepts and Algorithms; CHAPTER 3. Generalization and Abstraction in Markov Decision Processes; PART II. Sequential Decisions in the First-Order Setting; CHAPTER 4. Reasoning, Learning and Acting in Worlds with Objects; CHAPTER 5. Model-Free Algorithms for Relational MDPs.