Adaptive Markov Control Processes / Edition 1

by Onesimo Hernandez-Lerma

Overview

This book is concerned with a class of discrete-time shastic control processes known as controlled Markov processes (CMP's), also known as Markov decision processes or Markov dynamic programs. Starting in the mid-1950swith Richard Bellman, many contributions to CMP's have been made, and applications to engineering, statistics and operations research, among other areas, have also been developed. The purpose of this book is to present some recent developments on the theory of adaptive CMP's, i. e. , CMP's that depend on unknown parameters. Thus at each decision time, the controller or decision-maker must estimate the true parameter values, and then adapt the control actions to the estimated values. We do not intend to describe all aspects of shastic adaptive control; rather, the selection of material reflects our own research interests. The prerequisite for this book is a knowledgeof real analysis and prob­ ability theory at the level of, say, Ash (1972) or Royden (1968), but no previous knowledge of control or decision processes is required. The presentation, on the other hand, is meant to beself-contained,in the sensethat whenever a result from analysisor probability is used, it is usually stated in full and references are supplied for further discussion, if necessary. Several appendices are provided for this purpose. The material is divided into six chapters. Chapter 1 contains the basic definitions about the shastic control problems we are interested in; a brief description of some applications is also provided.

Product Details

ISBN-13:	9780387969664
Publisher:	Springer New York
Publication date:	05/01/1989
Series:	Applied Mathematical Sciences , #79
Edition description:	1989
Pages:	148
Product dimensions:	6.10(w) x 9.25(h) x 0.02(d)

Table of Contents

1 Controlled Markov Processes.- 1.1 Introduction.- 1.2 Shastic Control Problems.- 1.3 Examples.- 1.4 Further Comments.- 2 Discounted Reward Criterion.- 2.1 Introduction.- 2.2 Optimality Conditions.- 2.3 Asymptotic Discount Optimality.- 2.4 Approximation of MCM’s.- 2.5 Adaptive Control Models.- 2.6 Nonparametric Adaptive Control.- 2.7 Comments and References.- 3 Average Reward Criterion.- 3.1 Introduction.- 3.2 The Optimality Equation.- 3.3 Ergodicity Conditions.- 3.4 Value Iteration.- 3.5 Approximating Models.- 3.6 Nonstationary Value Iteration.- 3.7 Adaptive Control Models.- 3.8 Comments and References.- 4 Partially Observable Control Models.- 4.1 Introduction.- 4.2 PO-CM: Case of Known Parameters.- 4.3 Transformation into a CO Control Problem.- 4.4 Optimal I-Policies.- 4.5 PO-CM’s with Unknown Parameters.- 4.6 Comments and References.- 5 Parameter Estimation in MCM’s.- 5.1 Introduction.- 5.2 Contrast Functions.- 5.3 Minimum Contrast Estimators.- 5.4 Comments and References.- 6 Discretization Procedures.- 6.1 Introduction.- 6.2 Preliminaries.- 6.3 The Non-Adaptive Case.- 6.4 Adaptive Control Problems.- 6.5 Proofs.- 6.6 Comments and References.- Appendix A. Contraction Operators.- Appendix B. Probability Measures.- Total Variation Norm.- Weak Convergence.- Appendix C. Shastic Kernels.- Appendix D. Multifunctions and Measurable Selectors.- The Hausdorff Metric.- Multifunctions.- References.- Author Index.

Editorial Reviews

On that class of discrete-time stochastic control processes known as controlled Markov processes (CMPs). Presents some recent developments on the theory of adaptive CMPs. Annotation c. Book News, Inc., Portland, OR (booknews.com)

Booknews