Login / Signup
Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines.
Cathy Wu
Aravind Rajeswaran
Yan Duan
Vikash Kumar
Alexandre M. Bayen
Sham M. Kakade
Igor Mordatch
Pieter Abbeel
Published in:
ICLR (2018)
Keyphrases
</>
variance reduction
policy gradient
monte carlo
sample size
actor critic
importance sampling
naive bayes classifier
confidence intervals
reinforcement learning
gradient method
feature selection
optimal control
state action
particle filter
state space
computational complexity
bayesian networks