DATA-DRIVEN PRONTO iteratively estimates local linearized dynamics from perturbed closed-loop experiments, solves an LQR subproblem with those estimates, and provably converges to a neighborhood of the optimal solution whose size shrinks with the exploration dither amplitude.
Iterative learning control: Brief survey and categorization,
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DATA-DRIVEN PRONTO: a Model-free Solution for Numerical Optimal Control
DATA-DRIVEN PRONTO iteratively estimates local linearized dynamics from perturbed closed-loop experiments, solves an LQR subproblem with those estimates, and provably converges to a neighborhood of the optimal solution whose size shrinks with the exploration dither amplitude.