Tighter Bounds for Multi-Armed Bandits with Expert Advice.

H. Brendan McMahan Matthew J. Streeter

Published in: COLT (2009)

Keyphrases

expert advice
multi armed bandits
regret bounds
multi armed bandit
upper bound
loss bounds
lower bound
bandit problems
online learning
worst case
linear regression
dynamic programming
particle filter
learning algorithm
special case
pairwise
e learning