Robust physics (e.g., governing equations and laws) discovery is of great interest for many engineering fields explainable machine learning. A critical challenge compared with general training that the term format are not known as a prior. In addition, significant measurement noise complex algorithm hyperparameter tuning usually reduces robustness existing methods. robust data-driven method pro...

This paper considers the Linear Quadratic Regulator problem for linear systems with unknown dynamics, a central in data-driven control and reinforcement learning. We propose method that uses data to directly return controller without estimating model of system. Sufficient conditions are given under which this returns stabilizing guaranteed relative error when used design affected by noise. has ...