Relearn LQR combines recursive least squares with policy gradient for on-policy data-driven LQR and proves stability of the full scheme via Lyapunov analysis with averaging and timescale separation.
Low-complexity learning of linear quadratic regulators from noisy data
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
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.
Sequences of SDPs jointly produce online stabilizing controllers and Lyapunov certificates for nonlinear systems while certifying recursive feasibility and estimating the region of attraction.
citing papers explorer
-
Stability-Certified On-Policy Data-Driven LQR via Recursive Learning and Policy Gradient
Relearn LQR combines recursive least squares with policy gradient for on-policy data-driven LQR and proves stability of the full scheme via Lyapunov analysis with averaging and timescale separation.
-
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.
-
Semi-definite programs for online control of nonlinear systems with stability guarantees
Sequences of SDPs jointly produce online stabilizing controllers and Lyapunov certificates for nonlinear systems while certifying recursive feasibility and estimating the region of attraction.