Factored Contextual Policy Search with Bayesian Optimization.

Robert Pinsler Péter Karkus Andras Gabor Kupcsik David Hsu Wee Sun Lee

Published in: CoRR (2019)

Keyphrases

policy search
bayesian networks
optimization method
monte carlo methods
machine learning
state space
reinforcement learning
dynamic programming
mobile robot
markov chain
random walk
function approximation