Stochastic Learning and Optimization

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 is a multi-disciplinary area which has been attracting wide attention across many disciplines. Areas such as perturbation analysis (PA) in discrete event dynamic systems (DEDSs), Markov decision processes (MDPs) in operations research, reinforcement learning (RL) or neuro-dynamic programming (NDP) in computer science, identification and adaptive control (I&AC) in control systems, share the common goal: to make the "best decision" to optimize system performance.

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.

• Computer
• Markov Chains
• Markov decision processes
• Operations Research
• calculus
• ergodic systems
• event based optimization
• identification and adaptive control
• optimization
• perturbation analysis
• programming
• queueing systems
• reinforcement learning
• robot
• stochastic approximation

From the reviews:

"The book is written by known contributor to the theory of Markov decision problems and the theory of queueing systems and it is chiefly based on recent results obtained by the author. … The book provide good introductory materials for graduate students and engineers who wish to have an overview of learning and optimization theory, the related methodologies in different disciplines and their relations. Moreover, the book is useful in finding new research topics and in practical applications." (Vladimir Sobolev, Zentralblatt MATH, Vol. 1130, 2008)

"The systems studied in this book are stochastic dynamic systems … . The book is very well written, and … they are often presented in an intuitive way so that the study is really enjoyable. … the subject of the book is very important and very interesting. … It is intended for teachers, researchers, and graduate students who can recognize the practical and theoretical value of the methods described … . strongly recommended for scholars in engineering, mathematics, computer science, artificial intelligence, and machine learning." (Lefteris Angelis, ACM Computing Reviews, Vol. 49 (12), December, 2008)

"The key point of this monograph is perturbation analysis … . The book has appendices on Markov processes, stochastic matrices and queueing theory. Every chapter contains a number of problems for self-study. Along with known/proved statements, the reader can find many open problems for future research. Finally, the book can become the basis for several undergraduate lecture courses." (Aleksey B. Piunovskiy, Mathematical Reviews, Issue 2009 f)

• Hong Kong University of Science and Technology, Kowloon, Hong Kong

  Xi-Ren Cao

Policies and ethics