Reinforcement learning : an introduction / Richard S. Sutton and Andrew G. Barto.

Author/creator Sutton, Richard S. author.
Other author Barto, Andrew G., author.
Format Electronic
EditionSecond edition.
PublicationCambridge, Massachusetts : The MIT Press, [2018]
Copyright Date©2018
Description1 online resource (xxii, 526 pages).
Supplemental ContentProQuest Ebook Central
Subjects

SeriesAdaptive computation and machine learning
Adaptive computation and machine learning. ^A474767
Contents 1. Introduction -- I. Tabular Solution Methods: 2. Multi-armed Bandits -- 3. Finite Markov Decision processes -- 4. Dynamic programming -- 5. Monte Carlo methods -- 6. Temporal-difference learning -- 7. n-step Bootstrapping -- 8. Planning and learning with tabular methods-- I. Approximate Solution Methods: 9. On-policy Prediction with Approximation-- 10. On-policy Control with Approximation-- 11. Oæ-policy Methods with Approximation -- 12. Eligibility Traces-- 13. Policy Gradient Methods-- III. Looking Deeper: 14. Psychology -- 15. Neuroscience -- 16. Applications and Case Studies -- 17. Frontiers
Abstract "Reinforcement learning, 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."-- Provided by publisher
Bibliography noteIncludes bibliographical references and index.
Issued in other formPrint version: Sutton, Richard S. Reinforcement learning. Second edition. Cambridge, Massachusetts : The MIT Press, [2018] 0262039249 9780262039246
ISBN9780262352703 (electronic bk.)
ISBN0262352702 (electronic bk.)
ISBN(hardcover alkaline paper)
ISBN(hardcover alkaline paper)