Normal view MARC view ISBD view

Reinforcement learning : an introduction / Richard S. Sutton and Andrew G. Barto

By:

Sutton, Richard S [author]

Material type: Text

TextPublication details: Cambridge, Massachusetts : The MIT Press, c2018Edition: Second EditionDescription: xviii, 524 pages : illustrations ; 24 cmISBN:

9798845864970

Subject(s):

REINFORCEMENT LEARNING

LOC classification:

Q 325.6 .S88 2018

Contents:

Summary of Notation -- I. Tabular Solution Methods -- II. Approximate Solution Methods -- III. Looking Deeper -- References -- Index.

Summary: 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.

Item type:

Books

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings
Item type	Current library	Home library	Collection	Call number	Copy number	Status	Date due	Barcode
Books	National University - Manila	LRC - Main General Circulation	Machine Learning	GC Q 325.6 .S88 2018 (Browse shelf(Opens below))	c.1	Available		NULIB000019547

Browsing LRC - Main shelves, Shelving location: General Circulation, Collection: Machine Learning Close shelf browser (Hides shelf browser)

Previous				No cover image available				Next
Previous	GC Q 325.5 .R38 2018 Hands-on reinforcement learning with Python : master reinforcement and deep reinforcement learning using openAI gym and tensorflow /	GC Q 325.6 .B49 2019 Applied reinforcement learning with Python : with OpenAI Gym, Tensorflow and Keras /	GC Q 325.6 .P53 2022 Deep reinforcement learning /	GC Q 325.6 .S88 2018 Reinforcement learning : an introduction /	GC Q 325.7 .C43 2018 Introduction to deep learning /	GC QA 76.5 .S545 2011 Discovering computers fundamentals 2011 : living in a digital world /	GC QA 76.6 .S36 2019 Computer networking : this book includes computer networking for beginners and beginners guide (All-in-One) /	Next

Includes bibliographical references and index.

Summary of Notation -- I. Tabular Solution Methods -- II. Approximate Solution Methods -- III. Looking Deeper -- References -- Index.

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.

There are no comments on this title.

to post a comment.