Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation.

Yannick Hogewind Thiago D. Simão Tal Kachman Nils Jansen

Published in: CoRR (2022)

Keyphrases

reinforcement learning
direct policy search
learning algorithm
state space
stochastic approximation
monte carlo
function approximation
intensity differences
multiscale
input image
image classification
image representation
optimal control
stochastic model