Description: Reinforcement Learning/Reprinted from Machine Learning, Vol 8, Nos 3-4, Hardcover by Sutton, Richard S. (EDT), ISBN 0792392345, ISBN-13 9780792392347, Like New Used, Free P&P in the UK Reinforcement learning is the learning of a mapping from situations to actions so as to maximize a scalar reward or reinforcement signal. The learner is not told which action to take, as in most forms of machine learning, but instead must discover which actions yield the highest reward by trying them. In the most interesting and challenging cases, actions may affect not only the immediate reward, but also the next situation, and through that all subsequent rewards. These two characteristics -- trial-and-error search and delayed reward -- are the most important distinguishing features of reinforcement learning. Reinforcement learning is both a new and a very old topic in AI. The term appears to have been coined by Minsk (1961), and independently in control theory by Walz and Fu (1965). The earliest machine learning research now viewed as directly relevant was Samuel's (1959) checker player, which used temporal-difference learning to manage delayed reward much as it is used today. Of course learning and reinforcement have been studied in psychology for almost a century, and that work has had a very strong impact on the AI/engineering work. One could in fact consider all of reinforcement learning to be simply the reverse engineering of certain psychological learning processes (. operant conditioning and secondary reinforcement). Reinforcement Learning is an edited volume of original research, comprising seven invited contributions by leading researchers.
Price: 183.94 GBP
Location: Castle Donington
End Time: 2024-12-04T01:07:31.000Z
Shipping Cost: 19.55 GBP
Product Images
Item Specifics
Return postage will be paid by: Buyer
Returns Accepted: Returns Accepted
After receiving the item, your buyer should cancel the purchase within: 30 days
Book Title: Reinforcement Learning/Reprinted from Machine Learning, Vol 8, No
Number of Pages: 172 Pages
Publication Name: Reinforcement Learning
Language: English
Publisher: Springer
Item Height: 235 mm
Subject: Computer Science, Physics
Publication Year: 1992
Type: Textbook
Item Weight: 960 g
Author: Richard S. Sutton
Item Width: 155 mm
Series: The Springer International Series in Engineering and Computer Science
Format: Hardcover
