Login / Signup
Variational Policy Gradient Method for Reinforcement Learning with General Utilities.
Junyu Zhang
Alec Koppel
Amrit Singh Bedi
Csaba Szepesvári
Mengdi Wang
Published in:
CoRR (2020)
Keyphrases
</>
gradient method
reinforcement learning
actor critic
policy gradient
optimal policy
image segmentation
function approximation
step size
action selection
optimization methods
machine learning
multiresolution
state space
document collections
free energy