How Training Data Impacts Performance in Learning-based Control

by   Armin Lederer, et al.

When first principle models cannot be derived due to the complexity of the real system, data-driven methods allow us to build models from system observations. As these models are employed in learning-based control, the quality of the data plays a crucial role for the performance of the resulting control law. Nevertheless, there hardly exist measures for assessing training data sets, and the impact of the distribution of the data on the closed-loop system properties is largely unknown. This paper derives - based on Gaussian process models - an analytical relationship between the density of the training data and the control performance. We formulate a quality measure for the data set, which we refer to as ρ-gap, and derive the ultimate bound for the tracking error under consideration of the model uncertainty. We show how the ρ-gap can be applied to a feedback linearizing control law and provide numerical illustrations for our approach.


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

Despite the existence of formal guarantees for learning-based control ap...

Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control

Learned models and policies can generalize effectively when evaluated wi...

Concurrent Learning Based Tracking Control of Nonlinear Systems using Gaussian Process

This paper demonstrates the applicability of the combination of concurre...

Adjustment formulas for learning causal steady-state models from closed-loop operational data

Steady-state models which have been learned from historical operational ...

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

Data-driven models are subject to model errors due to limited and noisy ...

Episodic Gaussian Process-Based Learning Control with Vanishing Tracking Errors

Due to the increasing complexity of technical systems, accurate first pr...

Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap

There is an ever-growing zoo of modern neural network models that can ef...

Please sign up or login with your details

Forgot password? Click here to reset