Budgeted Multi-Armed Bandits with Asymmetric Confidence Intervals.

Marco Heyden Vadim Arzamasov Edouard Fouché Klemens Böhm

Published in: CoRR (2023)

Keyphrases

confidence intervals
multi armed bandits
sample size
bandit problems
markov chain
multi class
stochastic systems
test set
monte carlo
multi armed bandit
stopping rules
roc curve
conditional probabilities
decision problems
objective function
steady state
error rate
upper bound