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. 1703.08972
17
55

Thompson Sampling for Linear-Quadratic Control Problems

27 March 2017
Marc Abeille
A. Lazaric
ArXivPDFHTML
Abstract

We consider the exploration-exploitation tradeoff in linear quadratic (LQ) control problems, where the state dynamics is linear and the cost function is quadratic in states and controls. We analyze the regret of Thompson sampling (TS) (a.k.a. posterior-sampling for reinforcement learning) in the frequentist setting, i.e., when the parameters characterizing the LQ dynamics are fixed. Despite the empirical and theoretical success in a wide range of problems from multi-armed bandit to linear bandit, we show that when studying the frequentist regret TS in control problems, we need to trade-off the frequency of sampling optimistic parameters and the frequency of switches in the control policy. This results in an overall regret of O(T2/3)O(T^{2/3})O(T2/3), which is significantly worse than the regret O(T)O(\sqrt{T})O(T​) achieved by the optimism-in-face-of-uncertainty algorithm in LQ control problems.

View on arXiv
Comments on this paper