Secure Linear Quadratic Regulator Using Sparse Model-Free Reinforcement Learning.

Bahare Kiumarsi Tamer Basar

Published in: CDC (2019)

Keyphrases

linear quadratic
model free reinforcement learning
optimal control
closed loop
vector valued
dynamical systems
policy gradient
gaussian model
reinforcement learning
high dimensional
dynamic programming
sparse representation
neural network
state space
scale space