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. 2010.13178
81
11
v1v2 (latest)

Geometric Exploration for Online Control

25 October 2020
Orestis Plevrakis
Elad Hazan
ArXiv (abs)PDFHTML
Abstract

We study the control of an \emph{unknown} linear dynamical system under general convex costs. The objective is minimizing regret vs. the class of disturbance-feedback-controllers, which encompasses all stabilizing linear-dynamical-controllers. In this work, we first consider the case of known cost functions, for which we design the first polynomial-time algorithm with n3Tn^3\sqrt{T}n3T​-regret, where nnn is the dimension of the state plus the dimension of control input. The T\sqrt{T}T​-horizon dependence is optimal, and improves upon the previous best known bound of T2/3T^{2/3}T2/3. The main component of our algorithm is a novel geometric exploration strategy: we adaptively construct a sequence of barycentric spanners in the policy space. Second, we consider the case of bandit feedback, for which we give the first polynomial-time algorithm with poly(n)Tpoly(n)\sqrt{T}poly(n)T​-regret, building on Stochastic Bandit Convex Optimization.

View on arXiv
Comments on this paper