The Cross-Entropy Method for Policy Search in Decentralized POMDPs.

Frans A. Oliehoek Julian F. P. Kooij Nikos A. Vlassis

Published in: Informatica (Slovenia) (2008)

Keyphrases

cross entropy
policy search
reinforcement learning
dynamic programming
least squares
machine learning
probabilistic model
training data
training set
reinforcement learning algorithms
partially observable markov decision processes