Average optimality in a Poissonian bandit with switching arms.

Doncho S. Donchev Alexander A. Yushkevich

Published in: Math. Methods Oper. Res. (1997)

Keyphrases

average cost
machine learning
optimal solution
markov chain
multi armed bandits
database
data sets
neural network
real world
search algorithm
hidden markov models
least squares
standard deviation
infinite horizon
bandit problems