Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization.

Taisuke Kobayashi

Published in: CoRR (2021)

Keyphrases

kullback leibler divergence
reinforcement learning
information theoretic
probability density function
mutual information
information theory
distance measure
kl divergence
learning algorithm
machine learning
multiscale
image analysis
graphical models
random variables