Variational Policy Search using Sparse Gaussian Process Priors for Learning Multimodal Optimal Actions.

Hikaru Sasaki Takamitsu Matsubara

Published in: CoRR (2021)

Keyphrases

gaussian process
policy search
bayesian framework
prior knowledge
learning algorithm
reinforcement learning
supervised learning
gaussian processes
decision theoretic
learning process
learning tasks
high dimensional
active learning
semi supervised
regression model
learning problems
machine learning