Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Krupa, Pablo, Hasnaouy, Hasna El, Zanon, Mario, Bemporad, Alberto
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.22502
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917110539616256
author Krupa, Pablo
Hasnaouy, Hasna El
Zanon, Mario
Bemporad, Alberto
author_facet Krupa, Pablo
Hasnaouy, Hasna El
Zanon, Mario
Bemporad, Alberto
contents In Model Predictive Control (MPC), the objective function plays a central role in determining the closed-loop behavior of the system, and must therefore be designed to achieve the desired closed-loop performance. However, in real-world scenarios, its design is often challenging, as it requires balancing complex trade-offs and accurately capturing a performance criterion that may not be easily quantifiable in terms of an objective function. This paper explores preference-based learning as a data-driven approach to constructing an objective function from human preferences over trajectory pairs. We formulate the learning problem as a machine learning classification task to learn a surrogate model that estimates the likelihood of a trajectory being preferred over another. The approach provides a surrogate model that can directly be used as an MPC objective function. Numerical results show that we can learn objective functions that provide closed-loop trajectories that align with the expressed human preferences.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22502
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning the MPC objective function from human preferences
Krupa, Pablo
Hasnaouy, Hasna El
Zanon, Mario
Bemporad, Alberto
Systems and Control
In Model Predictive Control (MPC), the objective function plays a central role in determining the closed-loop behavior of the system, and must therefore be designed to achieve the desired closed-loop performance. However, in real-world scenarios, its design is often challenging, as it requires balancing complex trade-offs and accurately capturing a performance criterion that may not be easily quantifiable in terms of an objective function. This paper explores preference-based learning as a data-driven approach to constructing an objective function from human preferences over trajectory pairs. We formulate the learning problem as a machine learning classification task to learn a surrogate model that estimates the likelihood of a trajectory being preferred over another. The approach provides a surrogate model that can directly be used as an MPC objective function. Numerical results show that we can learn objective functions that provide closed-loop trajectories that align with the expressed human preferences.
title Learning the MPC objective function from human preferences
topic Systems and Control
url https://arxiv.org/abs/2511.22502