Request Inspection Copy

If you are an Academic or Teacher and wish to consider this book as a prescribed textbook for your course, you may be eligible for a complimentary inspection copy. Please complete this form, including information about your position, campus and course, before adding to cart.

* Required Fields

To complete your Inspection Copy Request you will need to click the Checkout button in the right margin and complete the checkout formalities. You can include Inspection Copies and purchased items in the same shopping cart, see our Inspection Copy terms for further information.

Any Questions? Please email our text Support Team on text@footprint.com.au

Submit

Email this to a friend

* ALL required Fields

Order Inspection Copy

An inspection copy has been added to your shopping cart

Reinforcement Learning: an Introduction

by Richard S Sutton and AG Barto The MIT Press
Pub Date:
03/1998
ISBN:
9780262193986
Format:
Hbk 344 pages
Price:
AU$142.00 NZ$145.22
Product Status: New Edition Coming in July
add to your cart
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 Senior Research Scientist, Department of Computer Science,University of Massachusetts. Andrew G. Barto is Professor of Computer Science at the University ofMassachusetts.