A Posteriori Error Estimation for Control-Constrained, Linear-Quadratic Optimal Control Problems.

René Schneider Gerd Wachsmuth

Published in: SIAM J. Numer. Anal. (2016)

Keyphrases

optimal control
linear quadratic
optimal control problems
error estimation
dynamic programming
control strategy
reinforcement learning
model selection
control theory
control law
infinite horizon
control system
closed loop
supervised learning
dynamical systems
generalization error