Login / Signup
Control Regularization for Reduced Variance Reinforcement Learning.
Richard Cheng
Abhinav Verma
Gábor Orosz
Swarat Chaudhuri
Yisong Yue
Joel W. Burdick
Published in:
CoRR (2019)
Keyphrases
</>
reinforcement learning
optimal control
control problems
function approximation
control system
robotic control
control policy
action selection
data sets
covariance matrix
control strategies
learning problems
data acquisition
optimal policy
dynamic programming
feature space
learning algorithm