5 papers
Flowing Through States: Neural ODE Regularization for Reinforcement Learning
Mohamed Ghanem, Bernd Finkbeiner
Neural networks applied to sequential decision-making tasks typically rely on latent representations of environment states. While environment dynamics dictate how semantic states e…
Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models
Frederik Schmitt, Matthias Cosler, Niklas Metzger +4
Reactive synthesis, the problem of automatically constructing a hardware circuit from a logical specification, is a long-standing challenge in formal verification. It is elusive fo…
Universal Safety Controllers with Learned Prophecies
Bernd Finkbeiner, Niklas Metzger, Satya Prakash Nayak +1
\emph{Universal Safety Controllers (USCs)} are a promising logical control framework that guarantees the satisfaction of a given temporal safety specification when applied to any r…
Synthesis of Universal Safety Controllers
Bernd Finkbeiner, Niklas Metzger, Satya Prakash Nayak +1
The goal of logical controller synthesis is to automatically compute a control strategy that regulates the discrete, event-driven behavior of a given plant s.t. a temporal logic sp…
Information Flow Guided Synthesis with Unbounded Communication
Bernd Finkbeiner, Niklas Metzger, Yoram Moses
Information flow guided synthesis is a compositional approach to the automated construction of distributed systems where the assumptions between the components are captured as info…