Stochastic optimal control of unknown linear networked control system using Q-learning methodology.

Hao Xu S. Jagannathan

Published in: ACC (2011)

Keyphrases

networked control systems
state space
reinforcement learning
dynamic programming
mobile robot
control theory
function approximation
communication networks
long time delay
linear systems
pid controller
packet loss
learning rate
real time
least squares
social networks
learning algorithm