Sign in
Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States.
Noam Razin
Yotam Alexander
Edo Cohen-Karlik
Raja Giryes
Amir Globerson
Nadav Cohen
Published in:
CoRR (2024)
Keyphrases
</>
linear quadratic
optimal control
policy gradient
closed loop
control problems
dynamical systems
control strategy
vector valued
variance reduction
control system
reinforcement learning
markov chain
function approximation
gaussian model