Login / Signup
Thompson Sampling Achieves $\tilde{O}(\sqrt{T})$ Regret in Linear Quadratic Control.
Taylan Kargin
Sahin Lale
Kamyar Azizzadenesheli
Animashree Anandkumar
Babak Hassibi
Published in:
COLT (2022)
Keyphrases
</>
linear quadratic
optimal control
lower bound
vector valued
control system
closed loop
dynamical systems
worst case
image processing
control strategy
gaussian model
regret bounds
feature space
online learning
control method
online algorithms