Reinforcement Learning for Linear Quadratic Control is Vulnerable Under Cost Manipulation.

Yunhan Huang Quanyan Zhu

Published in: CoRR (2022)

Keyphrases

linear quadratic
optimal control
reinforcement learning
closed loop
control strategy
dynamic programming
dynamical systems
vector valued
control system
control method
special case
state space
supervised learning
medical images
learning algorithm
graphical models
random variables
mathematical model
learning problems