Login / Signup
Variational policy search using sparse Gaussian process priors for learning multimodal optimal actions.
Hikaru Sasaki
Takamitsu Matsubara
Published in:
Neural Networks (2021)
Keyphrases
</>
gaussian process
policy search
learning algorithm
learning process
reinforcement learning
prior knowledge
active learning
bayesian framework
dynamic programming
optimal solution
supervised learning
model selection
learning tasks
latent variables
gaussian processes
policy gradient