Power Search
Low Price Guarantee
We Take School POs
A Tutorial on Thompson Sampling
Contributor(s): Russo, Daniel J. (Author), Van Roy, Benjamin (Author), Kazerouni, Abbas (Author)

View larger image

 ISBN: 1680834703     ISBN-13: 9781680834703
Publisher: Now Publishers
OUR PRICE: $76.00  

Binding Type: Paperback - See All Available Formats & Editions
Published: July 2018
Qty:

Click for more in this series: Foundations and Trends(r) in Machine Learning
Additional Information
BISAC Categories:
- Computers | Machine Theory
Series: Foundations and Trends(r) in Machine Learning
Physical Information: 0.24" H x 6.14" W x 9.21" L (0.38 lbs) 112 pages
 
Descriptions, Reviews, Etc.
Publisher Description:
Thompson sampling is an algorithm for online decision problems where actions are taken sequentially in a manner that must balance between exploiting what is known to maximize immediate performance and investing to accumulate new information that may improve future performance. The algorithm addresses a broad range of problems in a computationally efficient manner and is therefore enjoying wide use. A Tutorial on Thompson Sampling covers the algorithm and its application, illustrating concepts through a range of examples, including Bernoulli bandit problems, shortest path problems, product recommendation, assortment, active learning with neural networks, and reinforcement learning in Markov decision processes. Most of these problems involve complex information structures, where information revealed by taking an action informs beliefs about other actions. It also discusses when and why Thompson sampling is or is not effective and relations to alternative algorithms.
 
Customer ReviewsSubmit your own review
 
To tell a friend about this book, you must Sign In First!