Reinforcement Learning -
-20% with code BOOKS
Shipping in 17-23 days
30-day return policy
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 t ... Full description
You May Also Like
TOP
The Demon-Haunted World: Science as a Candle in the Dark
-20% with code BOOKS
In stock at our supplier
TOP
Many Faces, One Purpose: A Managers Handbook on Women in Firefighting
U. S. Fire Administration, Homeland Security
-20% with code BOOKS
Out of stock
TOP
The Gulf Moment: Arab Relations Since 2011
Florence Gaub, U. S. Army War College, Strategic Studies Institute
-20% with code BOOKS
Out of stock
TOP
Introduction to Algorithms
Ronald L. Rivest, Charles E. Leiserson, Clifford Stein, Thomas H. Cormen
-20% with code BOOKS
In stock at our supplier
TOP
Thinking in Systems: International Bestseller
-20% with code BOOKS
In stock at our supplier
TOP
Integrating Special Forces and the ATLAS Network: A Theoretical Framework for Strategic Security Cooperation in Europe
-20% with code BOOKS
In stock at our supplier
TOP
The Code Book: The Science of Secrecy from Ancient Egypt to Quantum Cryptography
-20% with code BOOKS
In stock at our supplier
TOP
Skin in the Game: Hidden Asymmetries in Daily Life
-20% with code BOOKS
In stock at our supplier
TOP
Dinosaurs and Prehistoric Life: The Definitive Visual Guide to Prehistoric Animals
-20% with code BOOKS
In stock at our supplier
TOP
International Economics: Theory and Policy, Global Edition
Paul Krugman, Maurice Obstfeld, Marc Melitz
-20% with code BOOKS
In stock at our supplier
TOP
The Unaccountability Machine: Why Big Systems Make Terrible Decisions
-20% with code BOOKS
In stock at our supplier
TOP
Crossing Borders: About the birth of the Consortium of European Research Libraries, the organisation's early years and its path to maturity, spanning the period from the late twentieth century to the first decades of the twenty-first century
-20% with code BOOKS
In stock at our supplier
TOP
Cybernetics: Second Edition: Or the Control and Communication in the Animal and the Machine
-20% with code BOOKS
In stock at our supplier
TOP
101 Things I Learned in Architecture School
-20% with code BOOKS
In stock at our supplier
TOP
Einhundert Zitate Female Edition: Ein Postkartenbuch mit 100 Zitaten
-20% with code BOOKS
In stock at our supplier
Cook This Book: Techniques That Teach and Recipes to Repeat: A Cookbook
-20% with code BOOKS
In stock at our supplier
Description
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 (e.g. operant conditioning and secondary reinforcement). Reinforcement Learning is an edited volume of original research, comprising seven invited contributions by leading researchers.
More Information
| Publisher | Springer US |
|---|---|
| Series | The Springer International Series in Engineering and Computer Science |
| Release year | 1992 |
| Cover type | Hardcover |
| EAN | 9780792392347 |