Providing non-trivial certificates of safety for non-linear stochastic systems is an important
open problem. One promising solution to address this problem is the use of barrier functions …

Quantization replaces floating point arithmetic with integer arithmetic in deep neural network
models, providing more efficient on-device inference with less power and memory. In this …

We present for the first time a supermartingale certificate for ω-regular specifications. We
leverage the Robbins & Siegmund convergence theorem to characterize supermartingale …

This paper presents Fossil 2.0, a new major release of a software tool for the synthesis of
certificates (eg, Lyapunov and barrier functions) for dynamical systems modelled as ordinary …

We study the problem of learning controllers for discrete-time non-linear stochastic
dynamical systems with formal reach-avoid guarantees. This work presents the first method …

Reinforcement learning has shown promising results in learning neural network policies for
complicated control tasks. However, the lack of formal guarantees about the behavior of …

Multi-agent reinforcement learning (MARL) research is faced with a trade-off: it either uses
complex environments requiring large compute resources, which makes it inaccessible to …

The rapid advance of deep reinforcement learning techniques enables the oversight of
safety-critical systems through the utilization of Deep Neural Networks (DNNs). This …

Reinforcement learning has received much attention for learning controllers of deterministic
systems. We consider a learner-verifier framework for stochastic control systems and survey …

We present a novel method for the safety verification of nonlinear dynamical models that
uses neural networks to represent abstractions of their dynamics. Neural networks have …