Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning)

4.42 avg rating
( 243 ratings by Goodreads )
 
9780262193986: Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning)
View all copies of this ISBN edition:
 
 

Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications.

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 when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability.

The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.

"synopsis" may belong to another edition of this title.

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.

Review:

This is a highly intuitive and accessible introduction to the recent major developments in reinforcement learning, written by two of the field's pioneering contributors.

Dimitri P. Bertsekas and John N. Tsitsiklis, Professors, Department of Electrical Engineering andn Computer Science, Massachusetts Institute of Technology

This book not only provides an introduction to learning theory but also serves as a tremendous source of ideas for further development and applications in the real world.

Toshio Fukuda, Nagoya University, Japan; President, IEEE Robotics and Automantion Society

Reinforcement learning has always been important in the understanding of the driving force behind biological systems, but in the last two decades it has become increasingly important, owing to the development of mathematical algorithms. Barto and Sutton were the prime movers in leading the development of these algorithms and have described them with wonderful clarity in this new text. I predict it will be the standard text.

Dana Ballard, Professor of Computer Science, University of Rochester

The widely acclaimed work of Sutton and Barto on reinforcement learning applies some essentials of animal learning, in clever ways, to artificial learning systems. This is a very readable and comprehensive account of the background, algorithms, applications, and future directions of this pioneering and far-reaching work.

Wolfram Schultz, University of Fribourg, Switzerland

"About this title" may belong to another edition of this title.

Top Search Results from the AbeBooks Marketplace

1.

Richard S. Sutton, Andrew G. Barto
Published by A Bradford Book (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
New Hardcover Quantity Available: 1
Seller:
Ergodebooks
(RICHMOND, TX, U.S.A.)
Rating
[?]

Book Description A Bradford Book, 1998. Hardcover. Condition: New. Seller Inventory # DADAX0262193981

More information about this seller | Contact this seller

Buy New
US$ 49.66
Convert currency

Add to Basket

Shipping: US$ 3.99
Within U.S.A.
Destination, rates & speeds

2.

Sutton,
Published by MIT Press (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
New Quantity Available: > 20
Seller:
Books2Anywhere
(Fairford, GLOS, United Kingdom)
Rating
[?]

Book Description MIT Press, 1998. HRD. Condition: New. New Book. Shipped from UK in 4 to 14 days. Established seller since 2000. Seller Inventory # BB-9780262193986

More information about this seller | Contact this seller

Buy New
US$ 47.52
Convert currency

Add to Basket

Shipping: US$ 11.51
From United Kingdom to U.S.A.
Destination, rates & speeds

3.

Richard S. Sutton
Published by MIT Press Ltd
ISBN 10: 0262193981 ISBN 13: 9780262193986
New Hardcover Quantity Available: > 20
Seller:
THE SAINT BOOKSTORE
(Southport, United Kingdom)
Rating
[?]

Book Description MIT Press Ltd. Hardback. Condition: New. New copy - Usually dispatched within 2 working days. Seller Inventory # B9780262193986

More information about this seller | Contact this seller

Buy New
US$ 50.61
Convert currency

Add to Basket

Shipping: US$ 8.88
From United Kingdom to U.S.A.
Destination, rates & speeds

4.

Richard S. Sutton; Andrew G. Barto
Published by A Bradford Book (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
New Hardcover Quantity Available: 1
Seller:
Irish Booksellers
(Portland, ME, U.S.A.)
Rating
[?]

Book Description A Bradford Book, 1998. Condition: New. book. Seller Inventory # M0262193981

More information about this seller | Contact this seller

Buy New
US$ 57.14
Convert currency

Add to Basket

Shipping: US$ 3.27
Within U.S.A.
Destination, rates & speeds

5.

Richard S. Sutton, Andrew G. Barto
Published by MIT Press Ltd, United States (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
New Hardcover Quantity Available: 10
Seller:
Book Depository International
(London, United Kingdom)
Rating
[?]

Book Description MIT Press Ltd, United States, 1998. Hardback. Condition: New. Language: English. Brand new Book. Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications.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 when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability.The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning. Seller Inventory # AAU9780262193986

More information about this seller | Contact this seller

Buy New
US$ 60.45
Convert currency

Add to Basket

Shipping: FREE
From United Kingdom to U.S.A.
Destination, rates & speeds

6.

Richard S. Sutton, Andrew G. Barto, Francis Bach (editor)
Published by The MIT Press 1998-05-08, Cambridge, Mass. |London (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
New Hardcover Quantity Available: > 20
Seller:
Blackwell's
(Oxford, OX, United Kingdom)
Rating
[?]

Book Description The MIT Press 1998-05-08, Cambridge, Mass. |London, 1998. hardback. Condition: New. Seller Inventory # 9780262193986

More information about this seller | Contact this seller

Buy New
US$ 51.50
Convert currency

Add to Basket

Shipping: US$ 9.59
From United Kingdom to U.S.A.
Destination, rates & speeds

7.

Richard S. Sutton, Andrew G. Barto
Published by MIT Press Ltd, United States (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
New Hardcover Quantity Available: 10
Seller:
The Book Depository
(London, United Kingdom)
Rating
[?]

Book Description MIT Press Ltd, United States, 1998. Hardback. Condition: New. Language: English. Brand new Book. Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications.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 when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability.The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning. Seller Inventory # AAU9780262193986

More information about this seller | Contact this seller

Buy New
US$ 62.04
Convert currency

Add to Basket

Shipping: FREE
From United Kingdom to U.S.A.
Destination, rates & speeds

8.

Richard S. Sutton
ISBN 10: 0262193981 ISBN 13: 9780262193986
New Quantity Available: 1
Seller:
Bright Textbooks
(Aurora, CO, U.S.A.)
Rating
[?]

Book Description Condition: New. New Book. Seller Inventory # 0262193981-BTW

More information about this seller | Contact this seller

Buy New
US$ 62.85
Convert currency

Add to Basket

Shipping: FREE
Within U.S.A.
Destination, rates & speeds

9.

Sutton, Richard S.; Barto, Andrew G.
Published by MIT Press Ltd (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
New Hardcover Quantity Available: > 20
Rating
[?]

Book Description MIT Press Ltd, 1998. Condition: New. 1998. second edition. Hardcover. Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. Series: Adaptive Computation and Machine Learning Series. Num Pages: 344 pages, 108. BIC Classification: UYQM; UYQN. Category: (P) Professional & Vocational; (UP) Postgraduate, Research & Scholarly; (UU) Undergraduate. Dimension: 236 x 184 x 25. Weight in Grams: 804. . . . . . . Seller Inventory # V9780262193986

More information about this seller | Contact this seller

Buy New
US$ 64.63
Convert currency

Add to Basket

Shipping: FREE
From Ireland to U.S.A.
Destination, rates & speeds

10.

Richard S. Sutton; Andrew G. Barto
ISBN 10: 0262193981 ISBN 13: 9780262193986
New Quantity Available: 3
Seller:
Speedy Hen LLC
(Sunrise, FL, U.S.A.)
Rating
[?]

Book Description Condition: New. Bookseller Inventory # ST0262193981. Seller Inventory # ST0262193981

More information about this seller | Contact this seller

Buy New
US$ 65.15
Convert currency

Add to Basket

Shipping: FREE
Within U.S.A.
Destination, rates & speeds

There are more copies of this book

View all search results for this book