Nonlinear sequential accepts and rejects for identification of top arms in stochastic bandits.

Shahin Shahrampour Vahid Tarokh

Published in: Allerton (2017)

Keyphrases

multi armed bandits
stochastic systems
data sets
monte carlo
automatic identification
multi armed bandit problems
stochastic optimization
multi armed bandit
database
neural network
machine learning
multiscale
lower bound
high order
regret bounds
bandit problems