Regret bounds for online-learning-based linear quadratic control under database attacks.

Jafar Abbaszadeh Chekan Cedric Langbort

Published in: Autom. (2023)

Keyphrases

online learning
linear quadratic
regret bounds
optimal control
closed loop
e learning
control system
online convex optimization
vector valued
reinforcement learning
special case
upper bound
generative model