Data-Driven Abstraction and Synthesis for Stochastic Systems with Unknown Dynamics
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909765265784832 |
|---|---|
| author | Nazeri, Mahdi Badings, Thom Schmuck, Anne-Kathrin Soudjani, Sadegh Abate, Alessandro |
| author_facet | Nazeri, Mahdi Badings, Thom Schmuck, Anne-Kathrin Soudjani, Sadegh Abate, Alessandro |
| contents | We study the automated abstraction-based synthesis of correct-by-construction control policies for stochastic dynamical systems with unknown dynamics. Our approach is to learn an abstraction from sampled data, which is represented in the form of a finite Markov decision process (MDP). In this paper, we present a data-driven technique for constructing finite-state interval MDP (IMDP) abstractions of stochastic systems with unknown nonlinear dynamics. As a distinguishing and novel feature, our technique only requires (1) noisy state-input-state observations and (2) an upper bound on the system's Lipschitz constant. Combined with standard model-checking techniques, our IMDP abstractions enable the synthesis of policies that satisfy probabilistic temporal properties (such as "reach-while-avoid") with a predefined confidence. Our experimental results show the effectiveness and robustness of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15543 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Data-Driven Abstraction and Synthesis for Stochastic Systems with Unknown Dynamics Nazeri, Mahdi Badings, Thom Schmuck, Anne-Kathrin Soudjani, Sadegh Abate, Alessandro Systems and Control We study the automated abstraction-based synthesis of correct-by-construction control policies for stochastic dynamical systems with unknown dynamics. Our approach is to learn an abstraction from sampled data, which is represented in the form of a finite Markov decision process (MDP). In this paper, we present a data-driven technique for constructing finite-state interval MDP (IMDP) abstractions of stochastic systems with unknown nonlinear dynamics. As a distinguishing and novel feature, our technique only requires (1) noisy state-input-state observations and (2) an upper bound on the system's Lipschitz constant. Combined with standard model-checking techniques, our IMDP abstractions enable the synthesis of policies that satisfy probabilistic temporal properties (such as "reach-while-avoid") with a predefined confidence. Our experimental results show the effectiveness and robustness of our approach. |
| title | Data-Driven Abstraction and Synthesis for Stochastic Systems with Unknown Dynamics |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2508.15543 |