Exploitation of the Value Function in a Bilevel Optimal Control Problem.

Konstantin Palagachev Matthias Gerdts

Published in: System Modelling and Optimization (2015)

Keyphrases

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