11 papers
Converse Barrier Certificates for Set-Based Stochastic Reach-Avoid Verification
Bai Xue, C. -H. Luke Ong
Recent work established sufficient and necessary barrier-like conditions for infinite-horizon reach-avoid verification of stochastic discrete-time systems from a single initial sta…
Cost-Aware Adaptive Conformal Inference for Runtime Assurance in Dynamic Environments
Taoran Wu, Jingduo Pan, Luke Ong +1
This paper addresses the problem of providing runtime assurance for systems operating online under unknown and potentially time-varying data distributions. We propose Cost-Aware Ad…
Quantitative Verification of Finite-Time Constrained Occupation Measures for Continuous-time Stochastic Systems
Bai Xue, C. -H. Luke Ong
This paper addresses the quantitative verification of finite-time constrained occupation time for stochastic continuous-time systems governed by stochastic differential equations (…
Quantitative Verification of Constrained Occupation Time for Stochastic Discrete-time Systems
Bai Xue, Peixin Wang, C. -H. Luke Ong
This paper addresses the quantitative verification of constrained occupation time in stochastic discrete-time systems, focusing on the probability of visiting a target set at least…
PAC Finite-Time Safety Guarantees for Stochastic Systems with Unknown Disturbance Distributions
Taoran Wu, Dominik Wagner, C. -H. Luke Ong +1
We investigate the problem of establishing finite-time probabilistic safety guarantees for discrete-time stochastic dynamical systems subject to unknown disturbance distributions,…
When More Experts Hurt: Underfitting in Multi-Expert Learning to Defer
Shuqi Liu, Yuzhou Cao, Lei Feng +2
Learning to Defer (L2D) enables a classifier to abstain from predictions and defer to an expert, and has recently been extended to multi-expert settings. In this work, we show that…
Comparative Analysis of Barrier-like Function Methods for Reach-Avoid Verification in Stochastic Discrete-Time Systems
Zhipeng Cao, Peixin Wang, Luke Ong +3
In this paper, we compare several representative barrier-like conditions from the literature for infinite-horizon reach-avoid verification of stochastic discrete-time systems. Our…
PAC One-Step Safety Certification for Black-Box Discrete-Time Stochastic Systems
Taoran Wu, Dominik Wagner, Jingduo Pan +3
This paper investigates the problem of safety certification for black-box discrete-time stochastic systems, where both the system dynamics and disturbance distributions are unknown…
Refined Barrier Conditions for Finite-Time Safety and Reach-Avoid Guarantees in Stochastic Systems
Bai Xue, Luke Ong, Dominik Wagner +1
Providing finite-time probabilistic safety and reach-avoid guarantees is crucial for safety-critical stochastic systems. Existing state-of-the-art barrier methods often rely on a r…
Reinforcement Learning with LTL and -Regular Objectives via Optimality-Preserving Translation to Average Rewards
Xuan-Bach Le, Dominik Wagner, Leon Witzman +2
Linear temporal logic (LTL) and, more generally, -regular objectives are alternatives to the traditional discount sum and average reward objectives in reinforcement learning (RL…
Diagonalisation SGD: Fast & Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing
Dominik Wagner, Basim Khajwal, C. -H. Luke Ong
It is well-known that the reparameterisation gradient estimator, which exhibits low variance in practice, is biased for non-differentiable models. This may compromise correctness o…