Can we cope with the curse of dimensionality in optimal control by using neural approximators?

Riccardo Zoppoli Marcello Sanguineti Thomas Parisini

Published in: CDC (2001)

Keyphrases

optimal control
dynamic programming
control problems
network architecture
neural network
feedback control
control strategy
infinite horizon
reinforcement learning
class of nonlinear systems
optimal control problems
risk sensitive
brownian motion
lyapunov function
linear quadratic
machine learning
control law