Control-Oriented Learning on the Fly

Melkior Ornik, Steven Carr, Arie Israel, Ufuk Topcu

Research output: Contribution to journalArticlepeer-review

Abstract

This article focuses on developing a strategy for control of systems, whose dynamics are almost entirely unknown. This situation arises naturally in a scenario, where a system undergoes a critical failure. In that case, it is imperative to retain the ability to satisfy basic control objectives in order to avert an imminent catastrophe. To deal with limitations on the knowledge of system dynamics, we develop a theory of myopic control. At any given time, myopic control optimizes the current direction of the system trajectory, given solely the knowledge about system dynamics obtained from data until that time. We propose an algorithm that uses small perturbations in the control effort to learn system dynamics around the current system state, while ensuring that the system moves in a nearly optimal direction, and provide bounds for its suboptimality.

Original languageEnglish (US)
Article number8946327
Pages (from-to)4800-4807
Number of pages8
JournalIEEE Transactions on Automatic Control
Volume65
Issue number11
DOIs
StatePublished - Nov 2020

Keywords

  • Estimation
  • learning
  • optimal control
  • uncertain systems

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'Control-Oriented Learning on the Fly'. Together they form a unique fingerprint.

Cite this