Regret Bounds for Restless Markov Bandits.

Ronald Ortner Daniil Ryabko Peter Auer Rémi Munos

Published in: ALT (2012)

Keyphrases

regret bounds
semi markov
online learning
lower bound
linear regression
multi armed bandit
optimal control
upper bound
markov chain
conditional random fields
machine learning
image sequences
active learning
information theoretic
bregman divergences
linear predictors