Output feedback reinforcement Q-learning control for the discrete-time linear quadratic regulator problem.

Syed Ali Asad Rizvi Zongli Lin

Published in: CDC (2017)

Keyphrases

machine learning
linear quadratic
reinforcement learning
optimal control
closed loop
vector valued
dynamical systems
learning algorithm
gaussian model
state space
feedback control
dynamic programming
control strategy
control system
scale space
image processing
continuous state and action spaces