paper-with-me

Papers

Data-driven memory-dependent abstractions of dynamical systems

2022-12-04 · Adrien Banse, Licio Romao, Alessandro Abate, Raphaël M. Jungers

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.

📄 PDF Abstract BibTeX arXiv:2212.01926

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Data-driven memory-dependent abstractions of dynamical systems via a Cantor-Kantorovich metric

2024-05-14 · Adrien Banse, Licio Romao, Alessandro Abate, Raphaël M. Jungers

Abstractions of dynamical systems enable their verification and the design of feedback controllers using simpler, usually discrete, models. In this paper, we propose a data-driven abstraction mechanism based on a novel m…

Memory-dependent abstractions of stochastic systems through the lens of transfer operators

2025-02-06 · Adrien Banse, Giannis Delimpaltadakis, Luca Laurenti, Manuel Mazo Jr. 외

With the increasing ubiquity of safety-critical autonomous systems operating in uncertain environments, there is a need for mathematical methods for formal verification of stochastic models. Towards formally verifying pr…

Data-Driven Yet Formal Policy Synthesis for Stochastic Nonlinear Dynamical Systems

2025-01-02 · Mahdi Nazeri, Thom Badings, Sadegh Soudjani, Alessandro Abate

The automated synthesis of control policies for stochastic dynamical systems presents significant challenges. A standard approach is to construct a finite-state abstraction of the continuous system, typically represented…

Learning Dynamic Abstract Representations for Sample-Efficient Reinforcement Learning

2022-10-04 · Mehdi Dadvar, Rashmeet Kaur Nayyar, Siddharth Srivastava

In many real-world problems, the learning agent needs to learn a problem's abstractions and solution simultaneously. However, most such abstractions need to be designed and refined by hand for different problems and doma…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Data-driven Abstractions for Verification of Deterministic Systems

2022-11-03 · Rudi Coppola, Andrea Peruffo, Manuel Mazo Jr

A common technique to verify complex logic specifications for dynamical systems is the construction of symbolic abstractions: simpler, finite-state models whose behaviour mimics the one of the systems of interest. Typica…