Data-Driven Memory-Dependent Abstractions of Dynamical Systems
Abstract
We propose a sample-based, sequential method to abstract a (potentially black-box) dynamical system with a sequence of memory-dependent Markov chains of increasing size. We show that this approximation alleviates a correlation bias that has been observed in sample-based abstractions. We further propose a methodology to detect on the fly the memory length resulting in an abstraction with sufficient accuracy. We prove that, under reasonable assumptions, the method converges to a sound abstraction in some precise sense, and we showcase it on two case studies.
Cite
Text
Banse et al. "Data-Driven Memory-Dependent Abstractions of Dynamical Systems." Proceedings of The 5th Annual Learning for Dynamics and Control Conference, 2023.Markdown
[Banse et al. "Data-Driven Memory-Dependent Abstractions of Dynamical Systems." Proceedings of The 5th Annual Learning for Dynamics and Control Conference, 2023.](https://mlanthology.org/l4dc/2023/banse2023l4dc-datadriven/)BibTeX
@inproceedings{banse2023l4dc-datadriven,
title = {{Data-Driven Memory-Dependent Abstractions of Dynamical Systems}},
author = {Banse, Adrien and Romao, Licio and Abate, Alessandro and Jungers, Raphael},
booktitle = {Proceedings of The 5th Annual Learning for Dynamics and Control Conference},
year = {2023},
pages = {891-902},
volume = {211},
url = {https://mlanthology.org/l4dc/2023/banse2023l4dc-datadriven/}
}