Introduces regional excitation and proves high-probability, non-asymptotic RLS error bounds for sub-exponentially unstable nonlinear closed-loop systems, with O(sqrt(ln t/t)) convergence under global excitation.
Regret bounds for the adaptive control of linear quadratic systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.SY 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Non-Asymptotic Bounds for Closed-Loop Identification of Unstable Nonlinear Stochastic Systems
Introduces regional excitation and proves high-probability, non-asymptotic RLS error bounds for sub-exponentially unstable nonlinear closed-loop systems, with O(sqrt(ln t/t)) convergence under global excitation.