Log In Sign Up

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 ...

Control Barrier Functions for Unknown Nonlinear Systems using Gaussian Processes

This paper focuses on the controller synthesis for unknown, nonlinear sy...

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...

Safe learning-based trajectory tracking for underactuated vehicles with partially unknown dynamics

Underactuated vehicles have gained much attention in the recent years du...

Provably Robust Learning-Based Approach for High-Accuracy Tracking Control of Lagrangian Systems

Inverse dynamics control and feedforward linearization techniques are ty...

Anticipating the Long-Term Effect of Online Learning in Control

Control schemes that learn using measurement data collected online are i...