math.OCNov 13, 2026

Online Switching Control as Learning with Experts

Authors: Masataka Nakamura, Kaito Ito, Hideaki Ishii

Organizations: Department of Information Physics and Computing, The University of Tokyo, Tokyo, Japan

Abstract

This paper addresses the problem of online switching control for discrete-time nonlinear systems where a controller is sequentially selected from a finite set of candidates. The goal is to generate an adaptive sequence of controllers to minimize the cumulative cost under unknown disturbances and cost functions. Specifically, we consider a full-information feedback setting where realized disturbance effects and cost functions are available after each selection. Using counterfactual costs computed from historical data, we reduce the online switching control problem to the experts problem with switching costs. Then, we propose an adaptive switching algorithm based on the Hedge algorithm with a switching suppression mechanism. Notably, the proposed algorithm achieves an expected regret of O(Tlog⁡N)O(\sqrt{T\log N}), where TT is the time horizon and NN is the number of candidate controllers, while ensuring uniform boundedness of the state. This matches the optimal regret order for the standard experts problem.

Figures & tables

Explore similar work

CardsList
  1. Online Learning for Supervisory Switching Control

    Mar 16, 2026Haoyuan Sun, Ali JadbabaieOnline System Identification

  2. Revisiting Smoothed Online Learning: Competitive Ratio, Dynamic Regret with Switching Cost, and Best of Both Worlds

    Oct 17, 2026Lijun Zhang, Linzhe He, Wei Jiang +1Competitive AnalysisOnline Convex Optimization