Safe Policy Search with Gaussian Process Models.

Kyriakos Polymenakos Alessandro Abate Stephen J. Roberts

Published in: CoRR (2017)

Keyphrases

policy search
gaussian process models
gaussian processes
gaussian process
reinforcement learning
reinforcement learning algorithms
continuous state
human pose estimation
dynamic programming
regression model
state space
model selection
markov decision processes
reward function
cross validation
policy gradient