Online Nonstochastic Control with Convex Safety Constraints

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Nanfei, Hutchinson, Spencer, Alizadeh, Mahnoosh
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913670916734976
author Jiang, Nanfei
Hutchinson, Spencer
Alizadeh, Mahnoosh
author_facet Jiang, Nanfei
Hutchinson, Spencer
Alizadeh, Mahnoosh
contents This paper considers the online nonstochastic control problem of a linear time-invariant system under convex state and input constraints that need to be satisfied at all times. We propose an algorithm called Online Gradient Descent with Buffer Zone for Convex Constraints (OGD-BZC), designed to handle scenarios where the system operates within general convex safety constraints. We demonstrate that OGD-BZC, with appropriate parameter selection, satisfies all the safety constraints under bounded adversarial disturbances. Additionally, to evaluate the performance of OGD-BZC, we define the regret with respect to the best safe linear policy in hindsight. We prove that OGD-BZC achieves $\tilde{O} (\sqrt{T})$ regret given proper parameter choices. Our numerical results highlight the efficacy and robustness of the proposed algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18039
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Online Nonstochastic Control with Convex Safety Constraints
Jiang, Nanfei
Hutchinson, Spencer
Alizadeh, Mahnoosh
Optimization and Control
Systems and Control
This paper considers the online nonstochastic control problem of a linear time-invariant system under convex state and input constraints that need to be satisfied at all times. We propose an algorithm called Online Gradient Descent with Buffer Zone for Convex Constraints (OGD-BZC), designed to handle scenarios where the system operates within general convex safety constraints. We demonstrate that OGD-BZC, with appropriate parameter selection, satisfies all the safety constraints under bounded adversarial disturbances. Additionally, to evaluate the performance of OGD-BZC, we define the regret with respect to the best safe linear policy in hindsight. We prove that OGD-BZC achieves $\tilde{O} (\sqrt{T})$ regret given proper parameter choices. Our numerical results highlight the efficacy and robustness of the proposed algorithm.
title Online Nonstochastic Control with Convex Safety Constraints
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2501.18039