Stochastic Learning and Optimization: A Sensitivity-Based Approach (International Series on Discrete Event Dynamic Systems)

✍ Scribed by Xi-Ren Cao

• Publisher: Springer
• Year: 2007
• Tongue: English
• Leaves: 575
• Edition: 1
• Category: Library

✦ Synopsis

Performance optimization is vital in the design and operation of modern engineering systems, including communications, manufacturing, robotics, and logistics. Most engineering systems are too complicated to model, or the system parameters cannot be easily identified, so learning techniques have to be applied. This book provides a unified framework based on a sensitivity point of view. It also introduces new approaches and proposes new research topics within this sensitivity-based framework. This new perspective on a popular topic is presented by a well respected expert in the field.

✦ Table of Contents

cover......Page 1
Preface......Page 5
Contents......Page 13
1 Introduction......Page 453
2 Perturbation Analysis......Page 19
3 Learningand Optimization with Perturbation Analysis......Page 115
4 Markov Decision Processes......Page 151
5 Sample-Path-Based PolicyIteration......Page 221
6 ReinforcementLearning......Page 257
7 Adaptive Control Problems as MDPs......Page 309
8 Event-Based Optimization of Markov Systems......Page 353
9 Constructing Sensitivity Formulas......Page 421
Part III Appendices: MathematicalBackground......Page 501
A Probability and Markov Processes......Page 503
B Stochastic Matrices......Page 519
C Queueing Theory......Page 530
Notation and Abbreviations......Page 554
References......Page 557
Index......Page 572