Nonparametric infinite horizon Kullback-Leibler stochastic control.

Yunpeng Pan Evangelos A. Theodorou

Published in: ADPRL (2014)

Keyphrases

kullback leibler
infinite horizon
stochastic control
optimal control
distance measure
kullback leibler divergence
dynamic programming
control strategy
markov decision process
similarity measure
information theoretic
density estimation
learning algorithm
reinforcement learning
mutual information
optimal policy