Login / Signup
Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods.
Ching-An Cheng
Xinyan Yan
Byron Boots
Published in:
CoRL (2019)
Keyphrases
</>
variance reduction
policy gradient
policy gradient methods
control system
sample size
pairwise
control strategy
optimal control
natural actor critic
reinforcement learning
monte carlo
control strategies