S$90.85

FREE delivery: 1 - 4 June Details

Usually dispatched within 4 to 5 days.

Ships from and sold by The Book Depository Limited, from outside Singapore. For information about products sold by international sellers, click here.

Have one to sell?

Sell on Amazon

See all 4 images

Reinforcement Learning: An Introduction Hardcover – Illustrated, 13 November 2018

by Richard S. Sutton (Author), Andrew G. Barto (Author)

139 ratings

See all formats and editions Hide other formats and editions

Amazon Price

New from

Used from

Hardcover, Illustrated

S$90.85

—

Hardcover
S$90.85

10 New from S$90.85

Enhance your purchase

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.

Frequently bought together

Customers who viewed this item also viewed

Page 1 of 1 Start overPage 1 of 1

Ian Goodfellow
591
Hardcover
S$64.93
Stuart Russell
426
Paperback
S$61.96

Product details

Language : English
Hardcover : 552 pages
ISBN-10 : 0262039249
ISBN-13 : 978-0262039246
Reading age : 18 years and up

Best Sellers Rank: 4,015 in Books (See Top 100 in Books)
- 32 in Computer Science
- 74 in Graphics & Multimedia Software

Customer reviews:
139 ratings

Product description

About the Author

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.

What other items do customers buy after viewing this item?

Page 1 of 1 Start overPage 1 of 1

No customer reviews

5 star (0%)		0%
4 star (0%)		0%
3 star (0%)		0%
2 star (0%)		0%
1 star (0%)		0%

How are ratings calculated?

Review this product

Write a customer review

Most helpful customer reviews on Amazon.com

Amazon.com: 38 reviews

Taewan Kim

Very low print quality.

29 January 2019 - Published on Amazon.com

Verified Purchase

I know that this book is a bible of RL. However, the print quality is extremely low. For example, all figures in color are blurry and faint as if the book was printed with low toners/inks. I've already tried "replace order" to fix the book's bad hardcover quality, but looks like that wasn't the only problem. Unfortunately, now I only have a single option to return with a $0.00 value because this book is a replacement of my original order. Curious whether it's a problem of MIT Press or someone else...

68 people found this helpful

impersonal

Essential intuitions about Reinforcement Learning

29 November 2018 - Published on Amazon.com

Verified Purchase

I read the entire book cover to cover, doing every (non-programming) exercise, as part of a PhD involving RL. I was also familiar with the first edition (1998).

The 2nd edition (2018) has been entirely reworked; it is much longer, the structure has changed, the notation has changed, many new topics are discussed. Same as the first edition, the second edition is both a reference book and a pedagogic manual. The main differences are:

(1) Part I, which deals with the fundamentals of RL in a simplified setting, is carefully worded in order to convey understanding in the same accessible, intuitive manner as in the first edition, but also paying closer attention to mathematical rigor and systematicity.
(2) Part II, which deals with RL with function approximation, is at times somewhat involved mathematically compared to the first edition, reflecting the general evolution of the field of Machine Learning. The most difficult sections are clearly marked as such, and can be skipped. But taking on the difficulties straight on is always (positively) rewarding, in the end.
(3) Part III deals with related developments in psychology and neuroscience, which are a welcome addition to a field that has branched across disciplines. This should be useful to neuroscientists and computational neuroscientists, as well as to experimental/cognitive psychologists.

Many exercises are included. I am no math buff and found that I could do every single one of them on my own, which is unfortunately not usually the case in other A.I. books. These exercises serve to help the reader understand key issues by working them out for themselves, in a guided manner; they make self-study possible and enjoyable.

This is an indispensable book for anybody working in RL. My only issue is that I'm too late to be referenced in it, but I haven't lost hope of making it in the 3rd edition, which is expected in 2038.

45 people found this helpful

N Howe

Poor Quality Fake

31 January 2019 - Published on Amazon.com

Verified Purchase

This book would barely pass as an EE version of a textbook. At $57, the quality is utterly unacceptable. The spine feels like it's made of cheap cardboard and is not straight not does it cover all the pages. The covers are shorter than the pages. The spine bends over backwards when I pick up the book. The pages are not straight. The print quality is extremely low. I don't know how this happened but I am returning asap and will try to find an official copy of this book.

41 people found this helpful

Sergey S. Tambovskiy

Low quality print

2 February 2019 - Published on Amazon.com

Verified Purchase

Compared to Kindle version, printed version:
1. Contains figures of low-resolution with blurred colors: ex. in pages 29, 396 335, 422, 428, etc.
2. Thin & flimsy spine of the book
3. Pages contain paper defects
4. Looks like a fake print, definitely not from MIT Press

39 people found this helpful

Amazon Customer

Really bad

27 February 2019 - Published on Amazon.com

Verified Purchase

Book quality is so low, chapter 3 and 4 are repeated twice and only first 7 page of each chapter is in the book.

28 people found this helpful

Amazon Web Services Scalable Cloud Computing Services	Amazon Fresh Groceries & More Right To Your Door	Goodreads Book reviews & recommendations

Shopbop Designer Fashion Brands	AbeBooks Books, art & collectables	Alexa Actionable Analytics for the Web

Book Depository Books With Free Delivery Worldwide	IMDb Movies, TV & Celebrities	DPReview Digital Photography