Optimism in reinforcement learning and Kullback-Leibler divergence.

Sarah Filippi Olivier Cappé Aurélien Garivier

Published in: Allerton (2010)

Keyphrases

kullback leibler divergence
reinforcement learning
mutual information
information theoretic
probability density function
information theory
kl divergence
distance measure
machine learning
learning algorithm
diffusion tensor
marginal distributions
bayesian networks
supervised learning
expectation maximization