# Online switching control with stability and regret guarantees

arXiv: https://arxiv.org/abs/2301.08445 · HTML: https://mlsanity.com/paper/2301.08445/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jan 2023.

## Built on by (most cited first, 9 of 9)

- [Wakening Past Concepts without Past Data: Class-Incremental Learning from Online Placebos](https://mlsanity.com/paper/2310.16115/) (2023)
- [Learning the Uncertainty Sets for Control Dynamics via Set Membership: A Non-Asymptotic Analysis](https://mlsanity.com/paper/2309.14648/) (2023)
- [The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective](https://mlsanity.com/paper/2501.15910/) (2025)
- [Online Event-Triggered Switching for Frequency Control in Power Grids with Variable Inertia](https://mlsanity.com/paper/2408.15436/) (2024)
- [Anytime-Competitive Reinforcement Learning with Policy Prior](https://mlsanity.com/paper/2311.01568/) (2023)
- [A least-square method for non-asymptotic identification in linear switching control](https://mlsanity.com/paper/2404.08120/) (2024)
- [Data-Driven Adversarial Online Control for Unknown Linear Systems](https://mlsanity.com/paper/2308.08138/) (2023)
- [Online Learning for Supervisory Switching Control](https://mlsanity.com/paper/2603.14762/) (2026)
- [Self-Adaptive Learning and Model Predictive Control for Tracking Unknown Dynamics with No Regret](https://mlsanity.com/paper/2607.26370/) (2026)

## Abstract (arXiv)

This paper considers online switching control with a finite candidate controller pool, an unknown dynamical system, and unknown cost functions. The candidate controllers can be unstabilizing policies. We only require at least one candidate controller to satisfy certain stability properties, but we do not know which one is stabilizing. We design an online algorithm that guarantees finite-gain stability throughout the duration of its execution. We also provide a sublinear policy regret guarantee compared with the optimal stabilizing candidate controller. Lastly, we numerically test our algorithm on quadrotor planar flights and compare it with a classical switching control algorithm, falsification-based switching, and a classical multi-armed bandit algorithm, Exp3 with batches.