2021/03/15 by Deepan Muthirayan, Muthirayan, Deepan, Jianjun Yuan +3
Biochemistry, Genetics and Molecular Biology · Engineering · Medicine · #FOS: Electrical engineering #FOS: Mathematics #Influenza Virus Research Studies #Optimization and Control (math.OC) #Peroxisome Proliferator-Activated Receptors #Stability and Control of Uncertain Systems #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2103.08753
openalex publication_date 2021/03/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this work we consider the online control of a known linear dynamic system with adversarial disturbance and adversarial controller cost. The goal in online control is to minimize the regret, defined as the difference between cumulative cost over a period T and the cumulative cost for the best policy from a comparator class. For the setting we consider, we generalize the previously proposed online Disturbance Response Controller (DRC) to the adaptive gradient online Disturbance Response Controller. Using the modified controller, we present novel regret guarantees that improves the established regret guarantees for the same setting. We show that the proposed online learning controller is able to achieve intermediate intermediate regret rates between √(T) and logT for intermediate convex conditions, while it recovers the previously established regret results for general convex controller cost and strongly convex controller cost.