Best Arm Identification in Sample-path Correlated Bandits.

Rudrabhotla Sri Prakash Nikhil Karamchandani Sharayu Moharir

Published in: NCC (2022)

Keyphrases

sample path
stochastic systems
asymptotic analysis
markov chain
serial inventory systems
large deviations
policy iteration
average reward
lost sales
fluid model
multi armed bandit problems
upper bound
multistage
steady state