4 papers
Local Observability of a Class of Feedforward Neural Networks
Yi Yang, Victor G. Lopez, Matthias A. Müller
Beyond the traditional neural network training methods based on gradient descent and its variants, state estimation techniques have been proposed to determine a set of ideal weight…
On sample-based functional observability of linear systems
Isabelle Krauss, Victor G. Lopez, Matthias A. Müller
Sample-based observability characterizes the ability to reconstruct the internal state of a dynamical system by using limited output information, i.e., when measurements are only i…
Robust Stability of Gaussian Process Based Moving Horizon Estimation
Tobias M. Wolff, Victor G. Lopez, Matthias A. Müller
In this paper, we introduce a Gaussian process based moving horizon estimation (MHE) framework. The scheme is based on offline collected data and offline hyperparameter optimizatio…
An Efficient Off-Policy Reinforcement Learning Algorithm for the Continuous-Time LQR Problem
Victor G. Lopez, Matthias A. Müller
In this paper, an off-policy reinforcement learning algorithm is designed to solve the continuous-time LQR problem using only input-state data measured from the system. Different f…