Presents a data-driven value iteration algorithm for output-feedback LQR that recovers the optimal state-feedback gain via a non-minimal realization constructed from Kreisselmeier's adaptive filter.
Convergence and sample complexity of gradient methods for the model-free linear–quadratic regulator problem,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
The stationary point of observer-based dynamic LQR is characterized by a pair of symmetric discrete-time Sylvester equations, and the usual separated LQR-plus-minimum-trace-observer design is not optimal.
Multitask LQG control via history-dependent lifting to LQR yields generalization bounds tied to bisimulation heterogeneity and reduces policy gradient variance proportionally to the number of training tasks.
citing papers explorer
-
Data-Driven Linear Quadratic Control Using Output-Feedback via Non-Minimal Realization
Presents a data-driven value iteration algorithm for output-feedback LQR that recovers the optimal state-feedback gain via a non-minimal realization constructed from Kreisselmeier's adaptive filter.
-
On the Optimization Landscape of Observer-based Dynamic Linear Quadratic Control
The stationary point of observer-based dynamic LQR is characterized by a pair of symmetric discrete-time Sylvester equations, and the usual separated LQR-plus-minimum-trace-observer design is not optimal.
-
Multitask LQG Control: Performance and Generalization Bounds
Multitask LQG control via history-dependent lifting to LQR yields generalization bounds tied to bisimulation heterogeneity and reduces policy gradient variance proportionally to the number of training tasks.