A reference-decoupled reformulation makes direct data-driven LQT equivalent to certainty-equivalence solutions and supports convergent offline and online DeePO algorithms.
arXiv preprint arXiv:2312.14788 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Regularized DDPC formulations are convex relaxations of bi-level identification-control problems, and the new A-DDPC algorithm outperforms prior regularized methods by lowering bias and variance errors.
citing papers explorer
-
Direct Data-Driven Linear Quadratic Tracking via Policy Optimization
A reference-decoupled reformulation makes direct data-driven LQT equivalent to certainty-equivalence solutions and supports convergent offline and online DeePO algorithms.
-
Regularization in Data-driven Predictive Control: A Convex Relaxation Perspective
Regularized DDPC formulations are convex relaxations of bi-level identification-control problems, and the new A-DDPC algorithm outperforms prior regularized methods by lowering bias and variance errors.