Factored Contextual Policy Search with Bayesian Optimization.

Péter Karkus Andras Gabor Kupcsik David Hsu Wee Sun Lee

Published in: CoRR (2016)

Keyphrases

policy search
reinforcement learning
state space
monte carlo methods
reinforcement learning algorithms
continuous action
neural network
dynamic programming
optimization method
bayesian networks
probability distribution
heuristic search
continuous state