Reinforcement Learning

By: Richard S. Sutton,Andrew G. Barto

Reinforcement Learning

  • Format: Hardback
  • Publisher: MIT Press Ltd
  • ISBN: 9780262193986
More product information
Back to top

Buy on Tesco Direct from:

Available from Tesco Tesco

£45.95 Save £13.78

£32.17

currently unavailable

Sorry, this product is currently unavailable.

Do you want us to email you when this product is back in stock?

Delivery Options

  • Delivery options will be shown at checkout (or enable JavaScript to show on this page).
E-Coupon

Clubcard Boost now on Make your vouchers go further

How does it work?

  1. Your vouchers are waiting for you at the Tesco direct checkout
  2. Add the vouchers you want to use and they will double automatically
  3. The value of your Boost vouchers will be taken from your order, saving you money

Bonus: If the value of your Boost vouchers is more than your order, you'll receive the difference in Clubcard points!

Continue shopping
seller-pdp-logo

We've carefully chosen all our Tesco Partners, to give you even more choice when you shop with us online.

  • Browse a wider range of specialist products, all in one place
  • Collect Clubcard points on every order
  • Stay protected with the Tesco Partner Guarantee – we’re here to support you when buying from an approved Tesco Partner.

Synopsis

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.

1 1
Close overlay and continue

We value your opinion

Leave quick feedback Or Complete our survey