Asymptotically Optimal Multi-Armed Bandit Activation Policies under Side Constraints.

Apostolos N. Burnetas Odysseas Kanavetas Michael N. Katehakis

Published in: CoRR (2018)

Keyphrases

asymptotically optimal
optimal policy
asymptotic optimality
multi armed bandit
holding cost
arrival rate
heavy traffic
machine learning
multi armed bandits
markov decision processes
call center
data mining
information systems
feature selection
multi agent
multi class