• Title: Reinforcement Learning: An Introduction, Second Edition
• Author(s) Richard S. Sutton and Andrew G. Barto
• Publisher: MIT Press, Cambridge, MA, 2018; eBook (Creative Commons Licensed)
• License(s): CC BY-NC-ND 2.0
• Hardcover: 522 pages
• eBook: PDF (548 pages)
• Language: English
• ISBN-10: 0262039249
• ISBN-13: 978-0262039246
• Share This:  

Book Description

Reinforcement Learning (RL), one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the field's key ideas and algorithms. This second edition has been significantly expanded and updated, presenting new topics and updating coverage of other topics.

Like the first edition, this second edition focuses on core online learning algorithms, with the more mathematical material set off in shaded boxes. The treatment to be accessible to readers in all of the related disciplines.

Part I covers as much of reinforcement learning as possible without going beyond the tabular case for which exact solutions can be found. Many algorithms presented in this part are new to the second edition, including UCB, Expected Sarsa, and Double Learning.

Part II extends these ideas to function approximation, with new sections on such topics as artificial neural networks and the Fourier basis, and offers expanded treatment of off-policy learning and policy-gradient methods.

Part III has new chapters on reinforcement learning's relationships to psychology and neuroscience, as well as an updated case-studies chapter including AlphaGo and AlphaGo Zero, Atari game playing, and IBM Watson's wagering strategy. The final chapter discusses the future societal impacts of reinforcement learning.

This book is the bible of reinforcement learning, and the new edition is particularly timely given the burgeoning activity in the field. No one with an interest in the problem of learning to act - student, researcher, practitioner, or curious nonspecialist - should be without it.

• Richard S. Sutton is a Canadian computer scientist and a Professor of Computing Science and AITF Chair in Reinforcement Learning and Artificial Intelligence at the University of Alberta, and also Distinguished Research Scientist at DeepMind.
• Andrew G. Barto is a professor of computer science at University of Massachusetts Amherst, and chair of the department since January 2007. His main research area is reinforcement learning.

• Amazon
• Amazon (1st Edition)

• Machine Learning
• Neural Networks and Depp Learning
• Artificial Intelligence
• Statistics, Mathematical Statistics, and SAS Programming
• Probability and Stochastic Processe

• Reinforcement Learning: An Introduction, Second Edition (Richard S. Sutton, et al)
• The Mirror Site (1) - PDF
• The Mirror Site (2) - PDF
• The First Edition - HTML
• Book Homepage (PDF, Errata, Code, Solutions, etc.)

• An Introduction to Deep Reinforcement Learning

  Deep reinforcement learning is the combination of reinforcement learning (RL) and deep learning. This field of research has recently been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine.

• Distributional Reinforcement Learning (Marc G. Bellemare, et al)

  Distributional reinforcement learning is a new mathematical formalism for thinking about decisions. This first comprehensive guide provides a new mathematical formalism for thinking about decisions from a probabilistic perspective.

• Reinforcement Learning and Optimal Control (Dimitri Bertsekas)

  The purpose of the book is to consider large and challenging multistage decision problems, which can be solved in principle by dynamic programming and optimal control, but their exact solution is computationally intractable.

• Algorithms for Reinforcement Learning (Csaba Szepesvari)

  This book focuses on those algorithms of reinforcement learning that build on the powerful theory of dynamic programming. It gives 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.

• The Hundred-Page Machine Learning Book (Andriy Burkov)

  Everything you really need to know in Machine Learning in a hundred pages! This book provides a great practical guide to get started and execute on ML within a few days without necessarily knowing much about ML apriori.

• Understanding Machine Learning: From Theory to Algorithms

  Explains the principles behind the automated learning approach and the considerations underlying its usage. Provides an extensive theoretical account of the fundamental ideas underlying machine learning and the mathematical derivations.

• Foundations of Machine Learning (Mehryar Mohri, et al)

  This book is a general introduction to machine learning. It covers fundamental modern topics in machine learning while providing the theoretical basis and conceptual tools needed for the discussion and justification of algorithms.

• Probabilistic Machine Learning: An Introduction (Kevin Murphy)

  This book is a comprehensive introduction to machine learning that uses probabilistic models and inference as a unifying approach. It is written in an informal, accessible style, complete with pseudo-code for the most important algorithms.

• Machine Learning Yearning (Andrew Ng)

  You will learn how to align on ML strategies in a team setting, as well as how to set up development (dev) sets and test sets. After finishing this book, you will have a deep understanding of how to set technical direction for a machine learning project.