CaltechAUTHORS
  A Caltech Library Service

Regret-optimal control in dynamic environments

Goel, Gautam and Hassibi, Babak (2020) Regret-optimal control in dynamic environments. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20201109-155541657

[img] PDF - Submitted Version
See Usage Policy.

329Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20201109-155541657

Abstract

We consider the control of linear time-varying dynamical systems from the perspective of regret minimization. Unlike most prior work in this area, we focus on the problem of designing an online controller which competes with the best dynamic sequence of control actions selected in hindsight, instead of the best controller in some specific class of controllers. This formulation is attractive when the environment changes over time and no single controller achieves good performance over the entire time horizon. We derive the structure of the regret-optimal online controller via a novel reduction to H_∞ control and present a clean data-dependent bound on its regret. We also present numerical simulations which confirm that our regret-optimal controller significantly outperforms the H₂ and H_∞ controllers in dynamic environments.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/2010.10473arXivDiscussion Paper
Additional Information:Copyright 2021 by the author(s).
Record Number:CaltechAUTHORS:20201109-155541657
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20201109-155541657
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:106574
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:10 Nov 2020 15:28
Last Modified:10 Nov 2020 15:28

Repository Staff Only: item control page