Richard S. Sutton and Andrew G. Barto
Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learn- ing 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 new edition focuses on core online learning algorithms, with the more mathematical material set off in shaded boxes. 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 with 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.
Richard S. Sutton is 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 Professor Emeritus in the College of Computer and Information Sciences at the University of Massachusetts Amherst.
Adaptive Computation and Machine Learning series
“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 nonspecial- ist-should be without it.”
– Pedro Domingos, Professor of Computer Science, University of Washington, and author of The Master Algorithm “Generations of reinforcement learning researchers grew up and were inspired by the first edition of Sutton and Barto’s book. The second edition is guaranteed to please previous and new readers: while the new edition significantly expands the range of topics covered (including artificial neural networks, Monte Carlo tree search, average reward maximization, and a chapter on classic and new applications), thus increasing breadth, the authors also manage to increase the depth of the presentation by using cleaner notation and disentangling various aspects of this immense topic. At the same time, the new edition retains the simplicity and directness of explanations, thus maintaining the great accessibility of the book to readers of all backgrounds. A fantastic book that I wholeheartedly recommend to those interested in using, developing, or under- standing reinforcement learning.”
– Csaba Szepesvari, Research Scientist at DeepMind and Professor of Computing Science, University of Alberta
“I recommend Sutton and Barto’s new edition of Reinforcement Learning to anybody who wants to learn about this increas- ingly important family of machine learning methods. This second edition expands on the popular first edition, covering to- day’s key algorithms and theory, illustrating these concepts using real-world applications that range from learning to control robots to learning to defeat the human world-champion Go player, and discussing fundamental connections between these computer algorithms and research on human learning from psychology and neuroscience.”
– Tom Mitchell, Professor of Computer Science, Carnegie Mellon University
“Still the seminal text on reinforcement learning-the increasingly important technique that underlies many of the most advanced Al systems today. Required reading for anyone seriously interested in the science of Al!”
– Demis Hassabis, Cofounder and CEO, DeepMind
“The second edition of Reinforcement Learning by Sutton and Barto comes at just the right time. The appetite for reinforce- ment learning among machine learning researchers has never been stronger, as the field has been moving tremendously in the last twenty years. If you want to fully understand the fundamentals of learning agents, this is the textbook to go to and get started with. It has been extended with modern developments in deep reinforcement learning while extending the scholarly history of the field to modern days. I will certainly recommend it to all my students and the many other graduate students and researchers who want to get the appropriate context behind the current excitement for RL.”
– Yoshua Bengio, Professor of Computer Science and Operations Research, University of Montreal.