Reinforcement Learning, second edition: An Introduction (Adaptive Computation and Machine Learning series)
Sutton, Richard S.; Barto, Andrew G.
Language: English
Published by Bradford Books, 2018
- Hardcover
- Used
Condition: Used - As new
US$ 63.43
Quantity: 2 available
Add to basketItem description from seller
Complete and unmarked. All pages present and readable, binding tight. No highlighting, underlining, or writing anywhere in the text. Cover and spine show minimal to no shelf wear. May have a remainder mark, a price sticker or its residue, or a previous owner's name on the inside cover. Access codes, CDs, DVDs, and other bundled supplements may not be included and should be assumed used or missing unless the listing explicitly states otherwise.
Seller Inventory # E6279C01001U
- Title
- Reinforcement Learning, second edition: An Introduction (Adaptive Computation and Machine Learning series)
- Author
- Sutton, Richard S.; Barto, Andrew G.
- Publisher
- Bradford Books
- Publication year
- 2018
- Condition
- As New
- Binding
- hardcover
- Language
- English
- ISBN 10
- 0262039249
- ISBN 13
- 9780262039246
- Edition
- 2nd Edition
- Item weight
- 42 ounces
- Dimensions
- 7x1x9
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.
"Synopsis" may belong to another edition of this title.
About the Author
Andrew G. Barto is Professor Emeritus in the College of Computer and Information Sciences at the University of Massachusetts Amherst.
"About the title" may belong to another edition of this title.
Shipping rates within U.S.A.
| Item | 4 to 10 business days | 2 to 5 business days |
|---|---|---|
| First item | US$ 0.00 | US$ 3.99 |
Payment methods
Store description
Top quality textbooks! Unbeatable prices!
Specialty
Mostly used textbooksSeller's business information
FREESIA LLC
2000 E 42ND ST STE C-351
ODESSA, TX U.S.A. 79762
Terms of sale
30 day return guarantee, with full refund including original shipping costs for up to 30 days after delivery if an item arrives misdescribed or damaged.