Controlling unknown linear dynamics with bounded multiplicative regret

Jacob Carruth, Maximilian F. Eggl, Charles Fefferman, Clarence W. Rowley, Melanie Weber

Research output: Contribution to journalArticlepeer-review


We consider a simple control problem in which the underlying dynamics depend on a parameter that is unknown and must be learned. We exhibit a control strategy which is optimal to within a multiplicative constant. While most authors find strategies which are successful as the time horizon tends to infinity, our strategy achieves lowest expected cost up to a constant factor for a fixed time horizon.

Original languageEnglish (US)
Pages (from-to)2185-2216
Number of pages32
JournalRevista Matematica Iberoamericana
Issue number7
StatePublished - 2022

All Science Journal Classification (ASJC) codes

  • General Mathematics


  • Bounded regret
  • LQR control
  • adaptive control
  • competitive ratio


Dive into the research topics of 'Controlling unknown linear dynamics with bounded multiplicative regret'. Together they form a unique fingerprint.

Cite this