Data-Driven Optimal Control of Affine Systems: A Linear Programming Perspective
Systems and Control
2022-07-12 v2 Systems and Control
Optimization and Control
Abstract
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.
Cite
@article{arxiv.2203.12044,
title = {Data-Driven Optimal Control of Affine Systems: A Linear Programming Perspective},
author = {Andrea Martinelli and Matilde Gargiani and Marina Draskovic and John Lygeros},
journal= {arXiv preprint arXiv:2203.12044},
year = {2022}
}