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

4,38 valoración promedio
( 176 valoraciones por Goodreads )
 
9780262193986: Reinforcement Learning: An Introduction (Adaptive Computation and Machine 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.

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.

"Sinopsis" puede pertenecer a otra edición de este libro.

About the Author:

Richard S. Sutton is Senior Research Scientist, Department of Computer Science, University of Massachusetts.

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)

"Sobre este título" puede pertenecer a otra edición de este libro.

Los mejores resultados en AbeBooks

1.

Richard S. Sutton
ISBN 10: 0262193981 ISBN 13: 9780262193986
Nuevos Cantidad: 14
Librería
Super textbook online
(Houston, TX, Estados Unidos de America)
Valoración
[?]

Descripción Estado de conservación: New. US Edition Book In Mint condition. Shipping with Trackable Method. Nº de ref. de la librería 0262193981-TOS

Más información sobre esta librería | Hacer una pregunta a la librería

Comprar nuevo
EUR 40,75
Convertir moneda

Añadir al carrito

Gastos de envío: GRATIS
A Estados Unidos de America
Destinos, gastos y plazos de envío

2.

Sutton, Richard S.
Editorial: MIT Press
ISBN 10: 0262193981 ISBN 13: 9780262193986
Nuevos Cantidad: > 20
Librería
TextbookRush
(Grandview Heights, OH, Estados Unidos de America)
Valoración
[?]

Descripción MIT Press. Estado de conservación: Brand New. Ships SAME or NEXT business day. We Ship to APO/FPO addr. Choose EXPEDITED shipping and receive in 2-5 business days within the United States. See our member profile for customer support contact info. We have an easy return policy. Nº de ref. de la librería 43386188

Más información sobre esta librería | Hacer una pregunta a la librería

Comprar nuevo
EUR 43,59
Convertir moneda

Añadir al carrito

Gastos de envío: EUR 3,38
A Estados Unidos de America
Destinos, gastos y plazos de envío

3.

Richard S. Sutton; Andrew G. Barto
Editorial: MIT Press 1998-05-08 (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
Nuevos Cantidad: 5
Librería
Chiron Media
(Wallingford, Reino Unido)
Valoración
[?]

Descripción MIT Press 1998-05-08, 1998. Estado de conservación: New. Brand new book, sourced directly from publisher. Dispatch time is 24-48 hours from our warehouse. Book will be sent in robust, secure packaging to ensure it reaches you securely. Nº de ref. de la librería NU-BER-00043948

Más información sobre esta librería | Hacer una pregunta a la librería

Comprar nuevo
EUR 47,15
Convertir moneda

Añadir al carrito

Gastos de envío: EUR 3,37
De Reino Unido a Estados Unidos de America
Destinos, gastos y plazos de envío

4.

Sutton, Richard S.; Barto, Andrew G.
Editorial: MIT Press Ltd (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
Nuevos Tapa dura Cantidad: > 20
Librería
Valoración
[?]

Descripción MIT Press Ltd, 1998. Estado de conservación: New. 1998. 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. . . . . . . Nº de ref. de la librería V9780262193986

Más información sobre esta librería | Hacer una pregunta a la librería

Comprar nuevo
EUR 53,88
Convertir moneda

Añadir al carrito

Gastos de envío: GRATIS
De Irlanda a Estados Unidos de America
Destinos, gastos y plazos de envío

5.

Sutton, Richard S.
Editorial: MIT Press (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
Nuevos Cantidad: > 20
Librería
Books2Anywhere
(Fairford, GLOS, Reino Unido)
Valoración
[?]

Descripción MIT Press, 1998. HRD. Estado de conservación: New. New Book. Shipped from UK in 4 to 14 days. Established seller since 2000. Nº de ref. de la librería BB-9780262193986

Más información sobre esta librería | Hacer una pregunta a la librería

Comprar nuevo
EUR 44,61
Convertir moneda

Añadir al carrito

Gastos de envío: EUR 10,14
De Reino Unido a Estados Unidos de America
Destinos, gastos y plazos de envío

6.

Sutton, Richard S.; Barto, Andrew G.
Editorial: MIT Press Ltd
ISBN 10: 0262193981 ISBN 13: 9780262193986
Nuevos Tapa dura Cantidad: > 20
Librería
Kennys Bookstore
(Olney, MD, Estados Unidos de America)
Valoración
[?]

Descripción MIT Press Ltd. Estado de conservación: New. 1998. 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. . . . . . Books ship from the US and Ireland. Nº de ref. de la librería V9780262193986

Más información sobre esta librería | Hacer una pregunta a la librería

Comprar nuevo
EUR 57,67
Convertir moneda

Añadir al carrito

Gastos de envío: GRATIS
A Estados Unidos de America
Destinos, gastos y plazos de envío

7.

Richard S. Sutton, Andrew G. Barto
Editorial: The MIT Press 1998-05-08, Cambridge, Mass. |London (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
Nuevos Tapa dura Cantidad: > 20
Librería
Blackwell's
(Oxford, OX, Reino Unido)
Valoración
[?]

Descripción The MIT Press 1998-05-08, Cambridge, Mass. |London, 1998. hardback. Estado de conservación: New. Nº de ref. de la librería 9780262193986

Más información sobre esta librería | Hacer una pregunta a la librería

Comprar nuevo
EUR 51,42
Convertir moneda

Añadir al carrito

Gastos de envío: EUR 6,76
De Reino Unido a Estados Unidos de America
Destinos, gastos y plazos de envío

8.

Richard S. Sutton, Andrew G. Barto
Editorial: MIT Press Ltd, United States (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
Nuevos Tapa dura Cantidad: 10
Librería
The Book Depository US
(London, Reino Unido)
Valoración
[?]

Descripción MIT Press Ltd, United States, 1998. Hardback. Estado de conservación: 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. Nº de ref. de la librería AAU9780262193986

Más información sobre esta librería | Hacer una pregunta a la librería

Comprar nuevo
EUR 58,61
Convertir moneda

Añadir al carrito

Gastos de envío: GRATIS
De Reino Unido a Estados Unidos de America
Destinos, gastos y plazos de envío

9.

Richard S. Sutton, Andrew G. Barto
Editorial: MIT Press Ltd, United States (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
Nuevos Tapa dura Cantidad: 10
Librería
The Book Depository
(London, Reino Unido)
Valoración
[?]

Descripción MIT Press Ltd, United States, 1998. Hardback. Estado de conservación: 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. Nº de ref. de la librería AAU9780262193986

Más información sobre esta librería | Hacer una pregunta a la librería

Comprar nuevo
EUR 59,04
Convertir moneda

Añadir al carrito

Gastos de envío: GRATIS
De Reino Unido a Estados Unidos de America
Destinos, gastos y plazos de envío

10.

Richard Sutton
Editorial: MIT Press (1998)
ISBN 10: 0262193981 ISBN 13: 9780262193986
Nuevos Tapa dura Cantidad: > 20
Librería
Ria Christie Collections
(Uxbridge, Reino Unido)
Valoración
[?]

Descripción MIT Press, 1998. Estado de conservación: New. book. Nº de ref. de la librería ria9780262193986_rkm

Más información sobre esta librería | Hacer una pregunta a la librería

Comprar nuevo
EUR 59,25
Convertir moneda

Añadir al carrito

Gastos de envío: EUR 4,36
De Reino Unido a Estados Unidos de America
Destinos, gastos y plazos de envío

Existen otras copia(s) de este libro

Ver todos los resultados de su búsqueda