Reinforcement learning an introduction

• Main Author: Sutton, Richard S.
• Other Authors: Barto, Andrew G.
• Format: Electronic eBook
• Language: English
• Published: Cambridge, Mass. : MIT Press, ©1998.
• Series: Adaptive computation and machine learning.
• Subjects: Reinforcement learning.; Massachusetts Institute of Technology Press.; Cambridge (Mass.); elektronické knihy; electronic books
• ISBN: 9780262257053
• Physical Description: 1 online zdroj (xviii, 322 pages) : illustrations.

Presents the book "Reinforcement Learning: An Introduction," written by Richard S. Sutton and Andrew G. Barto and published by the Massachusetts Institute of Technology (MIT) Press in 1998. The book is a textbook targeted toward engineers and scientists in artificial intelligence, operatio...

Table of Contents:

• 1. Introduction
• 2. Evaluative feedback
• 3. The reinforcement learning problem
• 4. Dynamic programming
• 5. Monte carlo methods
• 6. Temporal-difference learning
• 7. Eligibility traces
• 8. Generalization and function approximation
• 9. Planning and learning
• 10. Dimensions of reinforcement learning
• 11. Case studies.