Reinforcement Learning

An Introduction

The Springer International Series in Engineering and Computer Science Band 173

Richard S. Sutton, Andrew G. Barto

Die Leseprobe wird geladen.
eBook
eBook
Fr. 90.90
Fr. 90.90
inkl. gesetzl. MwSt.
inkl. gesetzl. MwSt.
Sofort per Download lieferbar
Sofort per Download lieferbar
Sie können dieses eBook verschenken  i

Weitere Formate

Taschenbuch

Fr. 233.00

Accordion öffnen
  • Reinforcement Learning

    Springer Us

    Versandfertig innert 6 - 9 Werktagen

    Fr. 233.00

    Springer Us

gebundene Ausgabe

ab Fr. 110.00

Accordion öffnen
  • Reinforcement Learning

    MIT Press

    Versandfertig innert 1 - 2 Wochen

    Fr. 110.00

    MIT Press
  • Reinforcement Learning

    Springer Us

    Versandfertig innert 6 - 9 Werktagen

    Fr. 329.00

    Springer Us

eBook

ab Fr. 90.90

Accordion öffnen

Beschreibung

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.

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.

Produktdetails

Format ePUB i
Kopierschutz Ja i
Family Sharing Ja i
Text-to-Speech Ja i
Seitenzahl 344 (Printausgabe)
Erscheinungsdatum 26.02.1998
Sprache Englisch
EAN 9780262303842
Verlag MIT Press
Dateigröße 8855 KB

Weitere Bände von The Springer International Series in Engineering and Computer Science

Kundenbewertungen

Es wurden noch keine Bewertungen geschrieben.

  • Artikelbild-0