Regret and Convergence Bounds for a Class of Continuum-Armed Bandit Problems.

Published in: IEEE Trans. Autom. Control. (2009)

Keyphrases

bandit problems
multi armed bandits
decision problems
lower bound
multi armed bandit problems
exploration exploitation
rates of convergence
worst case
confidence bounds
upper bound
convergence rate
linear complementarity problem
utility function
decision makers
expected utility
multi class
computational complexity