Timo Philipp Gros

Universität des Saarlandes | UKS · Department of Computer Science

Neural networks (NN) are taking over ever more decisions thus far taken by humans, even though verifiable system-level guarantees are far out of reach. Neither is the verification technology available, nor is it even understood what a formal, meaningful, extensible, and scalable testbed might look like for such a technology. The present paper is an...

MoGym, is an integrated toolbox enabling the training and verification of machine-learned decision-making agents based on formal models, for the purpose of sound use in the real world. Given a formal representation of a decision-making problem in the JANI format and a reach-avoid objective, MoGym (a) enables training a decision-making agent with re...

Testing is a promising way to gain trust in neural action policies π. Previous work on policy testing in sequential decision making targeted environment behavior leading to failure conditions. But if the failure is unavoidable given that behavior, then π is not actually to blame. For a situation to qualify as a "bug" in π, there must be an alternat...

Neural networks (NN) are gaining importance in sequential de-cision-making. Deep reinforcement learning (DRL), in particular, is extremely successful in learning action policies in complex and dynamic environments. Despite this success however, DRL technology is not without its failures, especially in safety-critical applications: (i) the training...

With the proliferation of neural networks (NN), the need to analyze, and ideally verify, their behavior becomes more and more pressing. Significant progress has been made in the analysis of individual NN decision episodes, but the verification of NNs as part of larger systems remains a grand challenge. Deep statistical model checking (DSMC) is a re...

Artificial neural networks are being proposed for automated decision making under uncertainty in many visionary contexts, including high-stake tasks such as navigating autonomous cars through dense traffic. Against this background, it is imperative that the decision making entities meet central societal desiderata regarding dependability, perspicui...

Learning-based approaches for solving large sequential decision making problems have become popular in recent years. The resulting agents perform differently and their characteristics depend on those of the underlying learning approach. Here, we consider a benchmark planning problem from the reinforcement learning domain, the Racetrack, to investig...

Learning-based approaches for solving large sequential decision making problems have become popular in recent years. The resulting agents perform differently and their characteristics depend on those of the underlying learning approach. Here, we consider a benchmark planning problem from the reinforcement learning domain, the Racetrack, to investig...

Neural networks (NN) are taking over ever more decisions thus far taken by humans, even though verifiable system-level guarantees are far out of reach. Neither is the verification technology available, nor is it even understood what a formal, meaningful, extensible, and scalable testbed might look like for such a technology. The present paper is a...