Stochastic linear-quadratic optimal control without time-consistency requirement.

Yuan-Hua Ni Ji-Feng Zhang

Published in: Commun. Inf. Syst. (2015)

Keyphrases

linear quadratic
optimal control
optimal control problems
dynamic programming
control problems
feedback control
control strategy
brownian motion
closed loop
reinforcement learning
dynamical systems
infinite horizon
vector valued
stochastic control