Login / Signup
PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation.
Matilde Gargiani
Andrea Zanelli
Andrea Martinelli
Tyler H. Summers
John Lygeros
Published in:
ICML (2022)
Keyphrases
</>
gradient estimation
gradient method
variance reduction
actor critic
policy gradient
probabilistic model
genetic algorithm
bayesian networks
text mining
generative model
optimization algorithm
optimal policy
missing data
optimization method
optimization methods
step size