A new proof of the discrete-time LQG optimal control theorems.

Mark H. A. Davis Mihail Zervos

Published in: IEEE Trans. Autom. Control. (1995)

Keyphrases

optimal control
optimal control problems
linear quadratic
control problems
dynamic programming
feedback control
reinforcement learning
class of nonlinear systems
control strategy
infinite horizon
control law
markov processes
machine learning
image segmentation
vector valued
stochastic control