3 papers
cs.AI2025
Composing Reinforcement Learning Policies, with Formal Guarantees
Florent Delgrange, Guy Avni, Anna Lukina +5
We propose a novel framework to controller design in environments with a two-level structure: a known high-level graph ("map") in which each vertex is populated by a Markov decisio…
cs.AI2025
In Search of Trees: Decision-Tree Policy Synthesis for Black-Box Systems via Search
Emir DemiroviÄ, Christian Schilling, Anna Lukina
Decision trees, owing to their interpretability, are attractive as control policies for (dynamical) systems. Unfortunately, constructing, or synthesising, such policies is a challe…
cs.LG2024
The Reachability Problem for Neural-Network Control Systems
Christian Schilling, Martin Zimmermann
A control system consists of a plant component and a controller which periodically computes a control input for the plant. We consider systems where the controller is implemented b…