GetTextbooks.com
 Compare Price & Save up to 90%
Search by multiple ISBN, single ISBN, title, author, etc ...

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

By Richard S. Sutton, Andrew G. Barto, Francis Bach (Series Editor)

ISBN: 9780262193986
ASIN: B01G3G41D6

Published: 1998

Number of Pages: 322

Edition: 1st

Binding: Hardcover


Pricing & Availability:
Additional Details:

Product Type: Book

Publisher: A Bradford Book

Description: 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.


Fixed-Length Data Elements - Additional Material Characteristics: m m d m u

Library of Congress Control Number
   - LC control Number:  97026416
   - LC control Number: 97026416
   - Canceled/invalid LC control number:  97026416
   - Canceled/invalid LC control number: 97026416

National Bibliography Number: GB98-36549

International Standard Book Number: 02621939810262193981 (alk. p0262193981 (alk. paper)0585024456 (electronic bk.)
   - Canceled/invalid ISBN: 0262193981

Level of Bibliographic Control and Coding Detail: //mb/cd(mb)/ROBA

Library of Congress Call Number
   - Classification number: Q325.6
   - Item number: .S88 1998
   - Item number: .S88 1998e
   - Item number: .S88 1998eb

Dewey Decimal Classification Number
   - Edition number: 21
   - Classification number: 006.3/1

Main Entry - Personal Name
   - Personal name: Sutton, Richard S
   - Personal name: Sutton, Richard S.

Title Statement
   - Title: Reinforcement learning
   - Title: Reinforcement learning :
   - Remainder of title: an introduction /
   - Statement of responsibility, etc.: Richard S. Sutton and Andrew G. Barto
   - Statement of responsibility, etc.: Richard S. Sutton and Andrew G. Barto .
   - Statement of responsibility, etc.: Richard S. Sutton and Andrew G. Barto.
   - Medium: [electronic resource]
   - Medium: [electronic resource] :

Publication, Distribution, etc. (Imprint)
   - Place of publication, distribution, etc.: [S.l.]
   - Place of publication, distribution, etc.: Cambridge, Mass. :
   - Name of publisher, distribution, etc.: MIT Press
   - Name of publisher, distribution, etc.: MIT Press,
   - Date of publication, distribution, etc.: c1998
   - Date of publication, distribution, etc.: c1998.

Physical Description
   - Extent: xviii, 322 p. :
   - Other physical details: ill. ;
   - Dimensions: 24 cm
   - Dimensions: 24 cm.

Series Statement/Added Entry - Title: Adaptive computation and machine learningAdaptive computation and machine learning.

General Note: "A Bradford Book."

Bibliography, etc. Note
   - Bibliography: Includes bibliographical references (p. [291]-312) and index
   - Bibliography: Includes bibliographical references (p. [291]-312) and index.
   - Bibliography: Includes bibliographical references (p. [291]-312) and index.

Formatted Contents Note
   - Miscellaneous information: 1.
   - Miscellaneous information: 10.
   - Miscellaneous information: 11.
   - Miscellaneous information: 2.
   - Miscellaneous information: 3.
   - Miscellaneous information: 4.
   - Miscellaneous information: 5.
   - Miscellaneous information: 6.
   - Miscellaneous information: 7.
   - Miscellaneous information: 8.
   - Miscellaneous information: 9.
   - Miscellaneous information: I.
   - Miscellaneous information: II.
   - Miscellaneous information: III.
   - Title: A Unified View --
   - Title: Case Studies --
   - Title: Contents --
   - Title: Dimensions of Reinforcement Learning --
   - Title: Dynamic Programming --
   - Title: Elementary Solution Methods --
   - Title: Eligibility Traces --
   - Title: Evaluative Feedback --
   - Title: Generalization and Function Approximation --
   - Title: Index.
   - Title: Introduction --
   - Title: Monte Carlo Methods --
   - Title: Planning and Learning --
   - Title: Preface --
   - Title: References --
   - Title: Series Foreword --
   - Title: Summary of Notation --
   - Title: Temporal-Difference Learning --
   - Title: The Problem --
   - Title: The Reinforcement Learning Problem --

Restrictions on Access Note
   - Terms governing access: Access restricted to subscribers.
   - Terms governing access: Licensed for access by U. of T. users.

Reproduction Note
   - Type of reproduction: Electronic reproduction.
   - Type of reproduction: PDF file.
   - Place of reproduction: Boulder, Colo. :
   - Agency responsible for reproduction: NetLibrary,
   - Date of reproduction: 2000.
   - Note about reproduction: Access may be limited to NetLibrary affiliated libraries
   - Note about reproduction: Access may be limited to NetLibrary affiliated libraries.
   - Note about reproduction: Available in multiple electronic file formats.
   - Note about reproduction: Available via the World Wide Web.
   - Note about reproduction: NetLibrary access available by license agreement to WWU Library users.

System Details Note: Mode of access: Internet.

Subject Added Entry - Topical Term
   - Topical term or geographic name entry element: Reinforcement learning (Machine learning)

Index Term - Genre/Form
   - Source of term: local
   - Source of term: local.
   - Genre/form data or focus term: Electronic books.

Added Entry - Personal Name
   - Personal name: Barto, Andrew G
   - Personal name: Barto, Andrew G.

Added Entry - Corporate Name
   - Corporate name or jurisdiction name as entry element: NetLibrary, Inc
   - Corporate name or jurisdiction name as entry element: NetLibrary, Inc.

Additional Physical Form Entry
   - Qualifying information: Original
   - Record control number: (DLC) 97026416
   - Record control number: (DLC) 97026416
   - Record control number: (DLC) 97026416
   - Record control number: (OCoLC)37293240
   - Record control number: (OCoLC)37293240.
   - International Standard Book Number: 0262193981


Home | iPhone App | Sell Books | Browse | Professors | Webmasters

[ Canada | United Kingdom | Germany | India ]

[ CDs | DVDs ]

Copyright © 2003-2024 GetTextbooks.com