joint assignment
Country:
- North America > United States > Texas > Brazos County > College Station (0.04)
- North America > United States > Michigan (0.04)
- Asia > Thailand > Bangkok > Bangkok (0.04)
Technology:
Country:
- North America > United States > Texas > Brazos County > College Station (0.04)
- North America > United States > Michigan (0.04)
- Asia > Thailand > Bangkok > Bangkok (0.04)
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (0.95)
- Information Technology > Artificial Intelligence > Robots (0.78)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models (0.68)
Graphical Models for Bandit Problems
Amin, Kareem, Kearns, Michael, Syed, Umar
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.
1202.3782
Country:
- North America > United States > Pennsylvania (0.04)
- North America > United States > New York (0.04)
- North America > United States > Nevada > Clark County > Las Vegas (0.04)
Technology:
- Information Technology > Data Science > Data Mining > Big Data (1.00)
- Information Technology > Artificial Intelligence > Machine Learning (1.00)