Reinforcement Learning, Second Edition
Format: Hardcover
ISBN13: 9780262039246
Hardcover|9780262039246
✨ Featured Offer
Brand New
$77.99
List Price: $100.00
🚚
See all 5 offers from $56.99 FREE standard delivery by: 03 Apr 2026
Overview
The significantly expanded and updated new edition of a widely used text on reinforcement learning, one of the most active research areas in artificial intelligence.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. 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. 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.
Like the first edition, this second 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 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.
| ISBN-13 | 9780262039246 |
|---|---|
| ISBN-10 | 0262039249 |
| Weight | 2.60 Pounds |
| Dimensions | 7.25 x 1.48 x 9.31 In |
| List Price | $100.00 |
| Edition | 2nd Edition |
| Format | Hardcover |
|---|---|
| Pages | 552 pages |
| Publisher | Bradford Books |
| Published On | 2018-11-13 |
View All Offers
Sort by:
Price
Condition
Seller
Seller Comments
Price
Used, Like New
Seller details
T & P LLC
HAMILTON, NJ, USA
Sewn binding. Cloth over boards. 552 p. Contains: Illustrations, black & white. Adaptive Computation...
Free delivery by: 03 Apr 2026
Used, Good
Seller details
Book Culture Inc.
New York, NY, USA
All pages and cover are intact. Possible minor highlighting and marginalia. Ships from an indie book...
Free delivery by: 03 Apr 2026
✨ Brand New
Seller details
T & P LLC
HAMILTON, NJ, USA
Sewn binding. Cloth over boards. 552 p. Contains: Illustrations, black & white. Adaptive Computation...
Free delivery by: 03 Apr 2026
Used, Good
Seller details
BooksRun
Philadelphia, PA, USA
It's a preowned item in good condition and includes all the pages. It may have some general signs ...
Free delivery by: 03 Apr 2026
Used, Very Good
Seller details
FirstClassBooks
Little Rock, AR, USA
Free delivery by: 03 Apr 2026