Saved in:
Bibliographic Details
Main Authors: Wang, Wenbin, Xu, Wenjie, Jones, Colin N.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.02225
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908918111797248
author Wang, Wenbin
Xu, Wenjie
Jones, Colin N.
author_facet Wang, Wenbin
Xu, Wenjie
Jones, Colin N.
contents Optimization with preference feedback is an active research area with many applications in engineering systems where humans play a central role, such as building control and autonomous vehicles. While most existing studies focus on optimizing a static user utility, few have investigated its closed-loop behavior that accounts for system transients. In this work, we propose an online feedback optimization controller that optimizes user utility using pairwise comparison feedback with both optimality and closed-loop stability guarantees. By adding a random exploration signal, the controller estimates the descent direction based on the binary comparison feedback between two consecutive time steps. We analyze its closed-loop behavior when interacting with a nonlinear plant and show that, under mild assumptions, the controller converges to the optimal point without inducing instability. Theoretical findings are further validated through numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02225
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Human-in-the-loop: Real-time Preference Optimization
Wang, Wenbin
Xu, Wenjie
Jones, Colin N.
Optimization and Control
Optimization with preference feedback is an active research area with many applications in engineering systems where humans play a central role, such as building control and autonomous vehicles. While most existing studies focus on optimizing a static user utility, few have investigated its closed-loop behavior that accounts for system transients. In this work, we propose an online feedback optimization controller that optimizes user utility using pairwise comparison feedback with both optimality and closed-loop stability guarantees. By adding a random exploration signal, the controller estimates the descent direction based on the binary comparison feedback between two consecutive time steps. We analyze its closed-loop behavior when interacting with a nonlinear plant and show that, under mild assumptions, the controller converges to the optimal point without inducing instability. Theoretical findings are further validated through numerical experiments.
title Human-in-the-loop: Real-time Preference Optimization
topic Optimization and Control
url https://arxiv.org/abs/2506.02225