A Framework for Adaptive Stabilisation of Nonlinear Stochastic Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Siriya, Seth, Zhu, Jingge, Nešić, Dragan, Pu, Ye
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909916391800832
author Siriya, Seth
Zhu, Jingge
Nešić, Dragan
Pu, Ye
author_facet Siriya, Seth
Zhu, Jingge
Nešić, Dragan
Pu, Ye
contents We consider the adaptive control problem for discrete-time, nonlinear stochastic systems with linearly parameterised uncertainty. Assuming access to a parameterised family of controllers that can stabilise the system in a bounded set within an informative region of the state space when the parameter is well-chosen, we propose a certainty equivalence learning-based adaptive control strategy, and subsequently derive stability bounds on the closed-loop system that hold for some probabilities. We then show that if the entire state space is informative, and the family of controllers is globally stabilising with appropriately chosen parameters, high probability stability guarantees can be derived.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17436
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Framework for Adaptive Stabilisation of Nonlinear Stochastic Systems
Siriya, Seth
Zhu, Jingge
Nešić, Dragan
Pu, Ye
Systems and Control
Machine Learning
Optimization and Control
We consider the adaptive control problem for discrete-time, nonlinear stochastic systems with linearly parameterised uncertainty. Assuming access to a parameterised family of controllers that can stabilise the system in a bounded set within an informative region of the state space when the parameter is well-chosen, we propose a certainty equivalence learning-based adaptive control strategy, and subsequently derive stability bounds on the closed-loop system that hold for some probabilities. We then show that if the entire state space is informative, and the family of controllers is globally stabilising with appropriately chosen parameters, high probability stability guarantees can be derived.
title A Framework for Adaptive Stabilisation of Nonlinear Stochastic Systems
topic Systems and Control
Machine Learning
Optimization and Control
url https://arxiv.org/abs/2511.17436