Learn and Control While Switching: Guaranteed Stability and Sublinear Regret

Jafar Abbaszadeh Chekan, Cedric Langbort

Research output: Contribution to journalArticlepeer-review

Abstract

Overactuated systems often make it possible to achieve specific performances by switching between different subsets of actuators. However, when the system parameters are unknown, transferring authority to different subsets of actuators is challenging due to stability and performance efficiency concerns. This article presents an efficient algorithm to tackle the so-called "learn and control while switching between different actuating modes"problem in the linear quadratic setting. Our proposed strategy is constructed upon optimism in the face of uncertainty (OFU)-based algorithm equipped with a projection toolbox to keep the algorithm efficient, regretwise. Along the way, we derive an optimum duration for the warm-up phase, thanks to the existence of a stabilizing neighborhood. The stability of the switched system is also guaranteed by designing a minimum average dwell time. The proposed strategy is proved to have a regret bound of OnsT in horizon T with ns number of switches, provably outperforming naively applying the basic OFU algorithm.

Original languageEnglish (US)
Pages (from-to)8433-8448
Number of pages16
JournalIEEE Transactions on Automatic Control
Volume69
Issue number12
DOIs
StatePublished - 2024
Externally publishedYes

Keywords

  • Overactuated system
  • regret
  • reinforcement learning
  • switched system

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Learn and Control While Switching: Guaranteed Stability and Sublinear Regret'. Together they form a unique fingerprint.

Cite this