arXiv:2203.12044
Data-Driven Optimal Control of Affine Systems: A Linear Programming Perspective
원문 초록
In this letter, we discuss the problem of optimal control for affine systems in the context of data-driven linear programming. First, we introduce a unified framework for the fixed point characterization of the value function, Q-function and relaxed Bellman operators. Then, in a model-free setting, we show how to synthesize and estimate Bellman inequalities from a small but sufficiently rich dataset. To guarantee exploration richness, we complete the extension of Willem's fundamental lemma to affine systems.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
On a Stochastic Fundamental Lemma and Its Use for Data-Driven Optimal Control
Identifying the Smallest Adversarial Load Perturbations that Render DC-OPF Infeasible
Distributed Lyapunov Functions for Nonlinear Networks
Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
Know When to Abstain: Optimal Selective Classification with Likelihood Ratios
Vulnerability of Transfer-Learned Neural Networks to Data Reconstruction Attacks in Small-Data Regime
토론
이 논문과 연결된 포럼 글이 아직 없습니다.