One Arrow, Two Kills: A Unified Framework for Achieving Optimal Regret Guarantees in Sleeping Bandits.

Pierre Gaillard Aadirupa Saha Soham Dan

Published in: AISTATS (2023)

Keyphrases

regret bounds
worst case
multi armed bandit
optimal solution
online learning
multi armed bandits
lower bound
multi armed bandit problems
real time
data sets
learning algorithm
optimal design
stochastic systems