Volume 27, 2021
|Number of page(s)||59|
|Published online||22 March 2021|
Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation*
University of Graz, Institute of Mathematics and Scientific Computing,
2 Johann Radon Institute for Computational and Applied Mathematics (RICAM), Austrian Academy of Sciences, Altenberger Straße 69, 4040 Linz, Austria.
** Corresponding author: email@example.com
Accepted: 15 January 2021
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. Second, an approximation to the feedback functions via realizations of neural networks. Based on universal approximation properties we prove the existence and convergence of optimal stabilizing neural network feedback controllers.
Mathematics Subject Classification: 49J15 / 49N35 / 68Q32 / 93B52 / 93D15
Key words: Optimal feedback stabilization / neural networks / Hamilton-Jacobi-Bellman equation / reinforcement learning
© EDP Sciences, SMAI 2021
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.