Check nearby libraries
Buy this book
Reinforcement learning is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with its environment. This book explains the main ideas and algorithms of reinforcement learning. The book is thorough in its coverage.
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.
Check nearby libraries
Buy this book
Previews available in: English
Subjects
Reinforcement learning (Machine learning), Reinforcement learning, Machine learning, Artificial intelligence, Operations research, Pattern recognition systems, Artificial Intelligence, Operations Research, Automated Pattern Recognition, Apprentissage par renforcement (Intelligence artificielle), Intelligence artificielle, Recherche opérationnelle, Reconnaissance des formes (Informatique), COMPUTERS, Enterprise Applications, Business Intelligence Tools, Intelligence (AI) & Semantics, Kunstmatige intelligentie, Reinforcement, Leren, Pattern recognition, automated, Q325.6 .s88 1998, 2012 f-947, Q 325.6, 006.3/1Showing 1 featured edition. View all 1 editions?
Edition | Availability |
---|---|
1 |
aaaa
Libraries near you:
WorldCat
|
Book Details
Edition Notes
Includes bibliographical references (p. [291]-312) and index.
Classifications
The Physical Object
ID Numbers
Community Reviews (0)
Feedback?December 19, 2023 | Edited by ImportBot | import existing book |
January 7, 2023 | Edited by MARC Bot | import existing book |
August 4, 2020 | Edited by ImportBot | import existing book |
January 26, 2018 | Edited by ImportBot | import new book |
December 10, 2009 | Created by WorkBot | add works page |