Data-Driven Adversarial Online Control for Unknown Linear Systems

TL;DR

This paper introduces a data-driven online adaptive control algorithm for unknown linear systems with adversarial disturbances, achieving near-optimal regret bounds without system identification.

Contribution

It proposes a novel data-driven control method leveraging behavioral systems theory and online gradient descent, extending to output feedback scenarios.

Findings

Achieves $ mO(T^{2/3})$ regret bound with high probability.

Extends the algorithm to output feedback cases.

Matches the best-known regret bounds for the problem.

Abstract

We consider the online control problem with an unknown linear dynamical system in the presence of adversarial perturbations and adversarial convex loss functions. Although the problem is widely studied in model-based control, it remains unclear whether data-driven approaches, which bypass the system identification step, can solve the problem. In this work, we present a novel data-driven online adaptive control algorithm to address this online control problem. Our algorithm leverages the behavioral systems theory to learn a non-parametric system representation and then adopts a perturbation-based controller updated by online gradient descent. We prove that our algorithm guarantees an $\tmO(T^{2/3})$ regret bound with high probability, which matches the best-known regret bound for this problem. Furthermore, we extend our algorithm and performance guarantee to the cases with output feedback.