Computer Science – Learning
Scientific paper
2012-02-14
Computer Science
Learning
Scientific paper
We introduce a rich class of graphical models for multi-armed bandit problems that permit both the state or context space and the action space to be very large, yet succinctly specify the payoffs for any context-action pair. Our main result is an algorithm for such models whose regret is bounded by the number of parameters and whose running time depends only on the treewidth of the graph substructure induced by the action space.
Amin Kareem
Kearns Michael
Syed Umar
No associations
LandOfFree
Graphical Models for Bandit Problems does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Graphical Models for Bandit Problems, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Graphical Models for Bandit Problems will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-90796