Optimism in Reinforcement Learning Based on Kullback-Leibler Divergence

Sarah Filippi Olivier Cappé Aurélien Garivier

Published in: CoRR (2010)

Keyphrases

kullback leibler divergence
reinforcement learning
mutual information
information theory
information theoretic
probability density function
distance measure
kl divergence
marginal distributions
machine learning
learning algorithm
feature selection
high dimensional
image registration
transfer learning