Perturbed-History Exploration in Stochastic Linear Bandits.

Branislav Kveton Csaba Szepesvári Mohammad Ghavamzadeh Craig Boutilier

Published in: UAI (2019)

Keyphrases

stochastic systems
regret bounds
closed form
monte carlo
databases
stochastic optimization
simple linear
transfer function
piecewise linear
linear model
visualization tool
high dimensional
data analysis
stochastic models
feature selection
data sets
multi armed bandit
multi armed bandits