Login / Signup
A stochastic multi-armed bandit approach to nonparametric H∞-norm estimation.
Matias I. Müller
Patricio E. Valenzuela
Alexandre Proutière
Cristian R. Rojas
Published in:
CDC (2017)
Keyphrases
</>
multi armed bandit
multi armed bandits
reinforcement learning
parametric models
density estimation
monte carlo
similarity measure
special case
mutual information
decentralized decision making