Reinforcement learning : an introduction / Richard S. Sutton and Andrew G. Barto.
By: Sutton, Richard S [author.].
Contributor(s): Barto, Andrew G [author.].
Material type: TextSeries: Adaptive computation and machine learning series.Publisher: Cambridge, Massachusetts : The MIT Press, [2018]Edition: Second edition.Description: xxii, 526 pages : Rs. 4450.00 illustrations (some color) ; 24 cm.Content type: text Media type: unmediated Carrier type: volumeISBN: 9780262039246 (hardcover : alk. paper).Subject(s): Reinforcement learningDDC classification: 006.3/1 Summary: "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.Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
---|---|---|---|---|---|---|
Book | Chennai Mathematical Institute General Stacks | 006.31 SUT (Browse shelf) | Checked out | 02/05/2024 | 10705 |
Browsing Chennai Mathematical Institute Shelves , Shelving location: General Stacks Close shelf browser
006.31 MUR Machine learning : a probabilistic perspective / | 006.31 QUI C4.5 : programs for machine learning / | 006.31 SCH Boosting : foundations and algorithms / | 006.31 SUT Reinforcement learning : an introduction / | 006.312 BAU Modern data science with R / | 006.333 RUS Artificial intelligence : a modern approach / | 006.35 IND Handbook of natural language processing / |
Includes bibliographical references (pages 481-518) and index.
"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.