Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation

Understand

A learning approach for optimal feedback gains for nonlinear continuous time control systems is proposed and analysed.

• The goal is to establish a rigorous framework for computing approximating optimal feedback gains using neural networks.
• The approach rests on two main ingredients.
• First, an optimal control formulation involving an ensemble of trajectories with 'control' variables given by the feedback gain functions.