The Value of Data in Learning-Based Control for Training Subset Selection

by   Armin Lederer, et al.

Despite the existence of formal guarantees for learning-based control approaches, the relationship between data and control performance is still poorly understood. In this paper, we present a measure to quantify the value of data within the context of a predefined control task. Our approach is applicable to a wide variety of unknown nonlinear systems that are to be controlled by a generic learning-based control law. We model the unknown component of the system using Gaussian processes, which in turn allows us to directly assess the impact of model uncertainty on control. Results obtained in numerical simulations indicate the efficacy of the proposed measure.


page 1

page 2

page 3

page 4


How Training Data Impacts Performance in Learning-based Control

When first principle models cannot be derived due to the complexity of t...

Neural Koopman Lyapunov Control

Learning and synthesizing stabilizing controllers for unknown nonlinear ...

Uniform Error and Posterior Variance Bounds for Gaussian Process Regression with Application to Safe Control

In application areas where data generation is expensive, Gaussian proces...

Stochastic Model Predictive Control Utilizing Bayesian Neural Networks

Integrating measurements and historical data can enhance control systems...

Learning Robust State Observers using Neural ODEs (longer version)

Relying on recent research results on Neural ODEs, this paper presents a...

Learning-based Control for PMSM Using Distributed Gaussian Processes with Optimal Aggregation Strategy

The growing demand for accurate control in varying and unknown environme...

Please sign up or login with your details

Forgot password? Click here to reset