Reinforcement Learning: An Introduction, 2nd Edition – Richard S. Sutton & Andrew G. Barto (Paperback)

Reinforcement Learning: An Introduction, 2nd Edition – Richard S. Sutton & Andrew G. Barto (Paperback)

Sale price  $59.99 Regular price $75.00
Skip to product information
Reinforcement Learning: An Introduction, 2nd Edition – Richard S. Sutton & Andrew G. Barto (Paperback)
Best Seller in Fiction

Reinforcement Learning: An Introduction, 2nd Edition – Richard S. Sutton & Andrew G. Barto (Paperback)

Amazon rating and customer reviews
Sale price  $59.99 Regular price $75.00
Flat $1 OFF on your first order
VISA AMEX
Publisher: The MIT Press
Author: Richard S. Sutton and Andrew G. Barto
Format: Physical Hardcover Book
  • Express Delivery: 3–4 business days ($14.99)
  • Standard Delivery: 4–5 business days ($6.99)
  • Free Shipping: 5–7 business days (all US orders)
  • Ships to the United States only
  • 15-Day Returns – see our Refund Policy
🏷️

Exclusive Offers For You

Choose your offer and copy the code!

SPECIAL OFFER

2% OFF

On orders above $999

BESTSELLER DEAL

5% OFF

On orders above $1999

In stock
Bulk Order

🚚 Choose Shipping Preference

Choose your preferred shipping option.

100% Genuine Books
Good condition book

Free Shipping

On orders over USA

Secure Payment

100% secure transactions

Easy Returns

15-day return policy

About Author

Richard S. Sutton is a renowned computer scientist and researcher in reinforcement learning and artificial intelligence. He is a Professor of Computing Science at the University of Alberta and has also worked as a Distinguished Research Scientist at DeepMind.

Andrew G. Barto is a computer scientist and Professor Emeritus at the University of Massachusetts Amherst. He is widely recognised for his foundational contributions to reinforcement learning research and artificial intelligence.

About Book

Reinforcement Learning: An Introduction, 2nd Edition by Richard S. Sutton and Andrew G. Barto is a foundational textbook on reinforcement learning, a major area of artificial intelligence and machine learning. It explains how intelligent agents learn to make decisions by interacting with an environment and maximizing cumulative rewards.

The book introduces fundamental concepts such as Markov decision processes, dynamic programming, Monte Carlo methods, temporal-difference learning, Q-learning, and policy-gradient methods. It also explores function approximation, artificial neural networks, planning algorithms, and applications of reinforcement learning in games, robotics, and other complex decision-making tasks.

Combining mathematical foundations with clear explanations and algorithmic examples, this book is designed for students, researchers, and developers seeking a deeper understanding of reinforcement learning theory and practice.

Key Features

  • Comprehensive introduction to reinforcement learning principles and algorithms

  • Covers Markov decision processes, dynamic programming, and Q-learning

  • Explains Monte Carlo and temporal-difference learning methods

  • Includes function approximation, neural networks, and policy-gradient techniques

  • Discusses practical applications and case studies in artificial intelligence

  • Suitable for students, researchers, and machine learning professionals

Product Details

Detail Information
Book Title Reinforcement Learning: An Introduction
Edition 2nd Edition
Authors Richard S. Sutton, Andrew G. Barto
Publisher The MIT Press
ISBN-13 9780262039246
ISBN-10 0262039249
Publication Date November 13, 2018
Language English
Binding Hardcover
Number of Pages 552
Format Physical Hardcover Book

 

A comprehensive textbook covering the principles and algorithms of reinforcement learning, including multi-armed bandits, Markov decision processes, dynamic programming, Monte Carlo methods, temporal-difference learning, function approximation, neural networks, and policy-gradient methods. The second edition includes updated algorithms, real-world AI case studies, and discussions of reinforcement learning applications in psychology and neuroscience.

Disclosures

Reinforcement Learning: An Introduction, 2nd Edition – Richard S. Sutton & Andrew G. Barto (Paperbac

Book Title: Reinforcement Learning: An Introduction, 2nd Edition

Authors: Richard S. Sutton, Andrew G. Barto

ISBN-13: 9780262039246

ISBN-10: 0262039249

Publisher: The MIT Press

Edition: 2nd Edition

Binding: Hardcover

Language: English

Number of Pages: 552

Publication Date: November 13, 2018

Product Condition: New

Format: Physical Hardcover Book

Frequently Bought Together

Finding related products...

You may also like