Algorithms for Reinforcement Learning by Csaba Szepesvári, University of Alberta
ISBN: 1608454924 / 9781608454921
Publication Date: July 2010
List Price: $35.00 / £19.99
Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. What distinguishes reinforcement learning from supervised learning is that only partial feedback is given to the learner about the learner’s predictions. Further, the predictions may have long term effects through influencing the future state of the controlled system. Thus, time plays a special role. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms’ merits and limitations. Reinforcement learning is of great interest because of the large number of practical applications that it can be used to address, ranging from problems in artificial intelligence to operations research or control engineering. In this book, we focus on those algorithms of reinforcement learning that build on the powerful theory of dynamic programming. We give a fairly comprehensive catalog of learning problems, describe the core ideas, note a large number of state of the art algorithms, followed by the discussion of their theoretical properties and limitations. Table of
Contents: Markov Decision Processes / Value Prediction Problems / Control / For Further Exploration
Download the book here: http://www.morganclaypool.com/doi/abs/10.2200/S00268ED1V01Y201005AIM009.
This title is available online free of charge to members of institutions that that have licensed the Synthesis Digital Library of Engineering and Computer Science. Use of this book as a course text is encouraged; and the text may be downloaded without restriction at licensing institutions, or after a one-time fee of $30.00 at non-licensing schools. To find out whether your institution is a subscriber, visit
Available titles and subject areas: http://www.morganclaypool.com/page/ForthcomingSynthesisLectures
Information for librarians, including pricing and license: http://www.morganclaypool.com/page/librarian_info
A review of Synthesis in ISTL: http://www.istl.org/09-winter/electronic.html
This book can also be purchased in paperback format directly from the Morgan & Claypool Bookstore for $35.00 USD, or from Amazon and other booksellers worldwide.
For more information and to request desk copies, please email andrea(at)morganclaypool.com.