An Asymptotically Optimal UCB Policy for Uniform Bandits of Unknown Support.

Wesley Cowan Michael N. Katehakis

Published in: CoRR (2015)

Keyphrases

asymptotically optimal
asymptotic optimality
heavy traffic
arrival rate
state dependent
holding cost
service rates
optimal policy
call center
learning algorithm
special case
online learning
intelligent agents
additive error