Bayesian ddLQR adds posterior uncertainty to the design, decomposing expected cost into certainty-equivalence plus variance terms, proving indirect-direct equivalence, and producing a data-length-independent SDP.
Formulas for data-driven control: Stabi- lization, optimality, and robustness,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
FAIL iteratively learns maximal state-control invariant sets from one-step failing state-input pairs for deterministic LTI systems with polytopic constraints, proving monotonic convergence to the true MSCI without dynamics knowledge.
A new regularized covariance parameterization enables effective direct data-driven LQR control for ill-conditioned data, shown equivalent to indirect Tikhonov-regularized LQR and extended to nonlinear systems via Koopman embedding.
citing papers explorer
-
A Bayesian Perspective on the Data-Driven LQR
Bayesian ddLQR adds posterior uncertainty to the design, decomposing expected cost into certainty-equivalence plus variance terms, proving indirect-direct equivalence, and producing a data-length-independent SDP.
-
Failure-Aware Iterative Learning of State-Control Invariant Sets
FAIL iteratively learns maximal state-control invariant sets from one-step failing state-input pairs for deterministic LTI systems with polytopic constraints, proving monotonic convergence to the true MSCI without dynamics knowledge.
-
On Tikhonov Regularization for Direct and Indirect Data-Driven LQR Control
A new regularized covariance parameterization enables effective direct data-driven LQR control for ill-conditioned data, shown equivalent to indirect Tikhonov-regularized LQR and extended to nonlinear systems via Koopman embedding.