Language : English
Published : 2010-04-23
Pages : 286
Reinforcement Learning and Dynamic Programming Using Function Approximators
From household appliances to applications in robotics, engineered systems involving complex dynamics can only be as effective as the algorithms that control them. While Dynamic Programming (DP) has provided researchers with a way to optimally solve decision and control problems involving complex dynamic systems, its practical value was limited by algorithms that lacked the capacity to scale up to realistic problems. However, in recent years, dramatic developments in Reinforcement Learning (RL), the model-free counterpart of DP, changed our understanding of what is possible. Those developments led to the creation of reliable methods that can be applied even when a mathematical model of the system is unavailable, allowing researchers to solve challenging control problems in engineering, as well as in a variety of other disciplines, including economics, medicine, and artificial intelligence. Reinforcement Learning and Dynamic Programming Using Function Approximators provides a comprehensive and unparalleled exploration of the field of RL and DP. With a focus on continuous-variable problems, this seminal text details essential developments that have substantially altered the field over the past decade. In its pages, pioneering experts provide a concise introduction to classical RL and DP, followed by an extensive presentation of the state-of-the-art and novel methods in RL and DP with approximation. Combining algorithm development with theoretical guarantees, they elaborate on their work with illustrative examples and insightful comparisons. Three individual chapters are dedicated to representative algorithms from each of the major classes of techniques: value iteration, policy iteration, and policy search. The features and performance of these algorithms are highlighted in extensive experimental studies on a range of control applications. The recent development of applications involving complex systems has led to a surge of interest in RL and DP methods and the subsequent need for a quality resource on the subject. For graduate students and others new to the field, this book offers a thorough introduction to both the basics and emerging methods. And for those researchers and practitioners working in the fields of optimal and adaptive control, machine learning, artificial intelligence, and operations research, this resource offers a combination of practical algorithms, theoretical analysis, and comprehensive examples that they will be able to adapt and apply to their own work. Access the authors’ website at www.dcsc.tudelft.nl/rlbook/ for additional material, including computer code used in the studies and information concerning new developments.
Pre-Order (3-4 weeks)
The first edition of “Microstrip Filters for RF/Microwave Applications” was published in 2001. Over the years the book has been well received and is used extensively in both academia and industry by microwave researchers and engineers. From its inception as a manuscript the book is almost 8 years old. While the fundamentals of filter circuits have not changed, further innovations in filter realizations and other applications have occurred with changes in the technology and use of new fabrication processes, such as the recent advances in RF MEMS and ferroelectric films for tunable filters; the use of liquid crystal polymer (LCP) substrates for multilayer circuits, as well as the new filters for dual-band, multi-band and ultra wideband (UWB) applications.
Although the microstrip filter remains as the main transmission line medium for these new developments, there has been a new trend of using combined planar transmission line structures such as co-planar waveguide (CPW) and slotted ground structures for novel physical implementations beyond the single layer in order to achieve filter miniaturization and better performance.
Also, over the years, practitioners have suggested topics that should be added for completeness, or deleted in some cases, as they were not very useful in practice.
In view of the above, the authors are proposing a revised version of the “Microstrip Filters for RF/Microwave Applications” text and a slightly changed book title of “Planar Filters for RF/Microwave Applications” to reflect the aforementioned trends in the revised book.
About the Author
Jia-Sheng Hong, PhD, is a senior faculty member in the Department of Electrical, Electronic, and Computer Engineering at Heriot-Watt University, Edinburgh, United Kingdom, where he leads a research group on advanced RF/microwave device technologies. Previously, he was involved with microwave applications of high-temperature superconductors, EM modeling, and circuit optimization at the University of Birmingham.
A major objective of this book is to fill the gap between traditional logic design principles and logic design/optimization techniques used in practice. Over the last two decades several techniques for computer-aided design and optimization of logic circuits have been developed. However, underlying theories of these techniques are inadequately covered or not covered at all in undergraduate text books. This book covers not only the “classical” material found in current text books but also selected materials that modern logic designers need to be familiar with.
About the Author
Parag K. Lala, PhD, DSc(Eng), is the Cary and Lois Patterson Chair of Electrical Engineering at Texas A&M University-Texarkana. Dr. Lala is the author of five books, including Fault-Tolerant and Fault-Testable Hardware Design and Practical Digital Logic Design and Testing. Dr. Lala was named a Fellow of the IEEE for “contributions to the development of self-checking logic and associated checker design.” He is also a Fellow of the Institution of Engineering and Technology, United Kingdom.
Social work is the profession that claims to intervene to enhance people’s well-being. However, social workers have played a low-key role in environmental issues that increasingly impact on people’s well-being, both locally and globally.
This compelling new contribution confronts this topic head-on, examining environmental issues from a social work perspective. Lena Dominelli draws attention to the important voice of practitioners working on the ground in the aftermath of environmental disasters, whether these are caused by climate change, industrial accidents or human conflict. The author explores the concept of ‘green social work’ and its role in using environmental crises to address poverty and other forms of structural inequalities, to obtain more equitable allocations of limited natural resources and to tackle global socio-political forces that have a damaging impact upon the quality of life of poor and marginalized populations at local levels. The resolution of these matters is linked to community initiatives that social workers can engage in to ensure that the quality of life of poor people can be enhanced without costing the Earth.
This important book will appeal to those in the fields of social work, social policy, sociology and human geography. It powerfully reveals how environmental issues are an integral part of social work’s remit if it is to retain its currency in the modern world and emphasize its relevance to the social issues that societies have to resolve in the twenty-first century.
About the Author
Lena Dominelli is Professor of Applied Social Sciences in the School of Applied Social Sciences, and Associate Director of the Institute of Hazard, Risk and Resilience Research at Durham University.
The Seventh Edition of Statistical Quality Control provides a comprehensive treatment of the major aspects of using statistical methodology for quality control and improvement. Both traditional and modern methods are presented, including state-of-the-art techniques for statistical process monitoring and control and statistically designed experiments for process characterization, optimization, and process robustness studies. The seventh edition continues to focus on DMAIC (define, measure, analyze, improve, and control–the problem-solving strategy of six sigma) including a chapter on the implementation process. Additionally, the text includes new examples, exercises, problems, and techniques. Statistical Quality Control is best suited for students in engineering, statistics, business and management science or students in undergraduate courses.