Retour aux activités
Séminaire informel de théorie des systèmes (ISS)

Relative Almost Sure Regret Bounds for Certainty Equivalence Control of Markov Jump Systems

iCalendar

24 avr. 2024   14h00 — 15h00

Borna Sayedana Université McGill, Canada

Borna Sayedana

Séminaire hybride à l'Université McGill ou Zoom.

In this talk, we consider the learning and control problem for unknown Markov jump linear systems (MJLS) with perfect state observations. We propose a certainty equivalence-based learning algorithm and show that this algorithm achieves a regret of O(\sqrt{T} log(T)) relative to a certain subset of the sample space. As part of our analysis, we propose a switched least squares method for the identification of MJLS, show that this method is strongly consistent, and derive data-dependent and data-independent rates of convergence. These results show that certainty equivalence control along with the switched least squares method for MJLS has the same rate of convergence as the certainty equivalence control method for linear systems.

Peter E. Caines responsable
Aditya Mahajan responsable
Shuang Gao responsable
Borna Sayedana responsable
Alex Dunyak responsable

Lieu

Salle MC 437
CIM
Pavillon McConnell
Université McGill
3480, rue University
Montréal QC H3A 0E9
Canada

Organisme associé

Centre for intelligent machines (CIM)

Axes de recherche

Applications de recherche