Regret Bounds for Satisficing in Multi-Armed Bandit Problems.

Thomas Michel Hossein Hajiabolhassan Ronald Ortner

Published in: Trans. Mach. Learn. Res. (2023)

Keyphrases

regret bounds
multi armed bandit problems
bandit problems
lower bound
online learning
linear regression
upper bound
multi armed bandit
online convex optimization
least squares
bayesian networks
optimal solution
sufficient conditions
convex optimization
decision theoretic