paper-with-me

홈 › Papers

Online Control of Linear Systems under Unbounded Noise

2024-02-15 · Kaito Ito, Taira Tsuchiya

This paper investigates the problem of controlling a linear system under possibly unbounded stochastic noise with unknown convex cost functions, known as an online control problem. In contrast to the existing work, which assumes the boundedness of noise, we show that an $ \tilde{O}(\sqrt{T}) $ high-probability regret can be achieved under unbounded noise, where $ T $ denotes the time horizon. Notably, the noise is only required to have a finite fourth moment. Moreover, when the costs are strongly convex and the noise is sub-Gaussian, we establish an $ O({\rm poly} (\log T)) $ regret bound.

📄 PDF Abstract BibTeX arXiv:2402.10252

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Predictive control for nonlinear stochastic systems: Closed-loop guarantees with unbounded noise

2024-07-18 · Johannes Köhler, Melanie N. Zeilinger

We present a stochastic model predictive control framework for nonlinear systems subject to unbounded process noise with closed-loop guarantees. First, we provide a conceptual shrinking-horizon framework that utilizes ge…

Computational EfficiencyFrictionModel Predictive Control

Stability Bounds for Learning-Based Adaptive Control of Discrete-Time Multi-Dimensional Stochastic Linear Systems with Input Constraints

2023-04-02 · Seth Siriya, Jingge Zhu, Dragan Nešić, Ye Pu

We consider the problem of adaptive stabilization for discrete-time, multi-dimensional linear systems with bounded control input constraints and unbounded stochastic disturbances, where the parameters of the true system …

parameter estimation

Online Nonstochastic Prediction: Logarithmic Regret via Predictive Online Least Squares

2026-05-06 · Chih-Fan Pai, Yang Zheng arxiv

We study online prediction for marginally stable, partially observed linear dynamical systems under nonstochastic disturbances. Our objective is to minimize the cumulative squared prediction loss and compete with the bes…

Stochastic Control Barrier Functions with Bayesian Inference for Unknown Stochastic Differential Equations

2023-12-20 · Chuanzheng Wang, Yiming Meng, Jun Liu, Stephen Smith

Control barrier functions are widely used to synthesize safety-critical controls. However, the presence of Gaussian-type noise in dynamical systems can generate unbounded signals and potentially result in severe conseque…

Bayesian Inference

End-to-end guarantees for indirect data-driven control of bilinear systems with finite stochastic data

2024-09-26 · Nicolas Chatzikiriakos, Robin Strässer, Frank Allgöwer, Andrea Iannelli

In this paper we propose an end-to-end algorithm for indirect data-driven control for bilinear systems with stability guarantees. We consider the case where the collected i.i.d. data is affected by probabilistic noise wi…

Learning Theory