Graphical Models for Bandit Problems
Machine Learning
2012-02-20 v1 Artificial Intelligence
Machine Learning
Abstract
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.
Cite
@article{arxiv.1202.3782,
title = {Graphical Models for Bandit Problems},
author = {Kareem Amin and Michael Kearns and Umar Syed},
journal= {arXiv preprint arXiv:1202.3782},
year = {2012}
}