AI & ML
Data-Driven Factored Abstractions of Stochastic Systems
arXiv cs.SY0 views
arXiv:2611.24663v1 Announce Type: new Abstract: Formal verification and correct-by-design policy synthesis for stochastic dynamical systems face significant scalability challenges due to the curse of dimensionality. These challenges are exacerbated when the system dynamics are unknown and abstractions must be constructed from data. This paper introduces a data-driven framework for constructing factored interval Markov decision process (fIMDP) abstractions from noisy transition observations. Assuming conditional independence of successor coordinates and known coordinate-wise Lipschitz bounds on the dynamics, the framework estimates marginal transition probabilities rather than joint probabilities, resulting in an exponential reduction in the number of probability entries to be estimated and stored. We establish finite-sample confidence guarantees that the abstraction captures the concrete transition probabilities uniformly over each abstract region, enabling certified lower bounds on satisfaction probabilities for $\omega$-regular specifications. Experiments on benchmark systems, including pendulum swing-up, unicycle control, and a four-dimensional planar robot model, demonstrate improvements in certified satisfaction probability lower bounds of up to 25 percentage points compared with a state-of-the-art flat IMDP abstraction method. Our framework required up to 23x less memory and was consistently faster in constructing the abstraction.
Source:https://arxiv.org/abs/2611.24663PreviousData-driven control of polynomial systems using implicit methodsNextCross-Vehicle Transferability of Lateral Velocity Estimation on Production Vehicles through Input Selection and Data Augmentation
Related posts
A Matching Lower Bound for Online Smooth Calibration
0arXiv stat.ML
How Path Integral Diffusion Decides a Finite Spin Glass
0arXiv stat.ML
Prescriptive Learning of Linear Policies with Feasibility Guarantees for Binary Decision-Making
0arXiv stat.ML
IQS-BO: In-Context Query Selection for Bayesian Optimisation
0arXiv stat.ML
Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time
0arXiv stat.ML
Inverse Design for Conditional Distribution Matching
0arXiv stat.ML