Data-driven memory-dependent abstractions of dynamical systems

Banse, Adrien;Romao, Licio;Abate, Alessandro;Jungers, Raphaƫl
(2022) 5th Learning for Dynamics & Control Conference

Files

l4dc23.pdf
  • Open Access
  • Adobe PDF
  • 599.23 KB
Download

Details

Authors
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 allows to alleviating 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.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Banse, A., Romao, L., Abate, A., & Jungers, R. (2022). Data-driven memory-dependent abstractions of dynamical systems. 5th Learning for Dynamics & Control Conference. https://hdl.handle.net/2078.5/252343