DeepAI
Log In Sign Up

How Training Data Impacts Performance in Learning-based Control

05/25/2020
by   Armin Lederer, et al.
0

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.

READ FULL TEXT
11/20/2020

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

Despite the existence of formal guarantees for learning-based control ap...
06/21/2022

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

Learned models and policies can generalize effectively when evaluated wi...
06/02/2021

Concurrent Learning Based Tracking Control of Nonlinear Systems using Gaussian Process

This paper demonstrates the applicability of the combination of concurre...
11/10/2022

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

Steady-state models which have been learned from historical operational ...
10/09/2022

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...
09/30/2019

H_2-gap model reduction for stabilizable and detectable systems

We formulate here an approach to model reduction that is well-suited for...
06/04/2020

GPHQP: Hierarchical Quadratic Programming for Controlling a Gaussian Process Regression Model of Redundant Robot

Accurate kinematic models are essential for effective control of surgica...