Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation.

Yannick Hogewind Thiago D. Simão Tal Kachman Nils Jansen

Published in: ICLR (2023)

Keyphrases

reinforcement learning
direct policy search
state space
function approximation
neural network
learning algorithm
face recognition
monte carlo
reinforcement learning algorithms
stochastic approximation