Reinforcement Learning: An Introduction
by Richard S. Sutton, Andrew G. Barto
Publisher: The MIT Press 2017
ISBN/ASIN: 0262193981
ISBN-13: 9780262193986
Number of pages: 445
Description:
Reinforcement learning is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In this book, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability.
Download or read it online for free here:
Download link
(12MB, PDF)
Similar books
A Survey of Statistical Network Modelsby A. Goldenberg, A.X. Zheng, S.E. Fienberg, E.M. Airoldi - arXiv
We begin with the historical development of statistical network modeling and then we introduce some examples in the network literature. Our subsequent discussion focuses on prominent static and dynamic network models and their interconnections.
(11039 views)
Statistical Learning and Sequential Predictionby Alexander Rakhlin, Karthik Sridharan - University of Pennsylvania
This text focuses on theoretical aspects of Statistical Learning and Sequential Prediction. The minimax approach, which we emphasize throughout the course, offers a systematic way of comparing learning problems. We will discuss learning algorithms...
(8860 views)
Gaussian Processes for Machine Learningby Carl E. Rasmussen, Christopher K. I. Williams - The MIT Press
Gaussian processes provide a principled, practical, probabilistic approach to learning in kernel machines. The treatment is comprehensive and self-contained, targeted at researchers and students in machine learning and applied statistics.
(32151 views)
Boosting: Foundations and Algorithmsby Robert E. Schapire, Yoav Freund - The MIT Press
Boosting is an approach to machine learning based on the idea of creating a highly accurate predictor by combining many weak and inaccurate 'rules of thumb'. A remarkably rich theory has evolved around boosting, with connections to a range of topics.
(8820 views)