ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2108.11563
30
10

Adaptive Control of Differentially Private Linear Quadratic Systems

26 August 2021
Sayak Ray Chowdhury
Xingyu Zhou
Ness B. Shroff
ArXivPDFHTML
Abstract

In this paper, we study the problem of regret minimization in reinforcement learning (RL) under differential privacy constraints. This work is motivated by the wide range of RL applications for providing personalized service, where privacy concerns are becoming paramount. In contrast to previous works, we take the first step towards non-tabular RL settings, while providing a rigorous privacy guarantee. In particular, we consider the adaptive control of differentially private linear quadratic (LQ) systems. We develop the first private RL algorithm, PRL, which is able to attain a sub-linear regret while guaranteeing privacy protection. More importantly, the additional cost due to privacy is only on the order of ln⁡(1/δ)1/4ϵ1/2\frac{\ln(1/\delta)^{1/4}}{\epsilon^{1/2}}ϵ1/2ln(1/δ)1/4​ given privacy parameters ϵ,δ>0\epsilon, \delta > 0ϵ,δ>0. Through this process, we also provide a general procedure for adaptive control of LQ systems under changing regularizers, which not only generalizes previous non-private controls, but also serves as the basis for general private controls.

View on arXiv
Comments on this paper