Algorithms for Reinforcement Learning
by Csaba Szepesvari
Publisher: Morgan and Claypool Publishers 2009
ISBN/ASIN: 1608454924
Number of pages: 98
Description:
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.
Download or read it online for free here:
Download link
(1.6MB, PDF)
Similar books

by David J. C. MacKay - Cambridge University Press
A textbook on information theory, Bayesian inference and learning algorithms, useful for undergraduates and postgraduates students, and as a reference for researchers. Essential reading for students of electrical engineering and computer science.
(26691 views)

by Dimitri P. Bertsekas - Athena Scientific
The book considers large and challenging multistage decision problems, which can be solved by dynamic programming and optimal control, but their exact solution is computationally intractable. We discuss solution methods that rely on approximations.
(7492 views)

by Aaron Hertzmann - University of Toronto
Contents: Introduction to Machine Learning; Linear Regression; Nonlinear Regression; Quadratics; Basic Probability Theory; Probability Density Functions; Estimation; Classification; Gradient Descent; Cross Validation; Bayesian Methods; and more.
(8857 views)

by Alex Smola, S.V.N. Vishwanathan - Cambridge University Press
Over the past two decades Machine Learning has become one of the mainstays of information technology and a rather central part of our life. Smart data analysis will become even more pervasive as a necessary ingredient for technological progress.
(8241 views)