1 code implementation • 5 Jul 2023 • Filip Cano Córdoba, Alexander Palmisano, Martin Fränzle, Roderick Bloem, Bettina Könighofer
We propose synthesis algorithms to compute \emph{delay-resilient shields} that guarantee safety under worst-case assumptions on the delays of the input signals.
1 code implementation • 4 Jul 2023 • Filip Cano Córdoba, Samuel Judson, Timos Antonopoulos, Katrine Bjørner, Nicholas Shoemaker, Scott J. Shapiro, Ruzica Piskac, Bettina Könighofer
We say that there is evidence of intentional behavior if the scope of agency is high and the decisions of the agent are close to being optimal for reaching the event.
no code implementations • 29 Jun 2023 • Martin Tappler, Edi Muškardin, Bernhard K. Aichernig, Bettina Könighofer
We aim to provide insights into the decisions faced by the agent by learning an automaton model of environmental behavior under the control of an agent.
no code implementations • 4 Dec 2022 • Bettina Könighofer, Julian Rudolf, Alexander Palmisano, Martin Tappler, Roderick Bloem
The intuition behind online shielding is to compute at runtime the set of all states that could be reached in the near future.
1 code implementation • 4 Dec 2022 • Martin Tappler, Stefan Pranger, Bettina Könighofer, Edi Muškardin, Roderick Bloem, Kim Larsen
Iteratively, we use the collected data to learn new MDPs with higher accuracy, resulting in turn in shields able to prevent more safety violations.
no code implementations • 30 Aug 2022 • Bettina Könighofer, Roderick Bloem, Rüdiger Ehlers, Christian Pek
In this paper, we are interested in techniques for constructing runtime enforcers for the concrete application domain of enforcing safety in AI.
no code implementations • 7 May 2022 • Martin Tappler, Filip Cano Córdoba, Bernhard K. Aichernig, Bettina Könighofer
We present a search-based testing framework that enables a wide range of novel analysis capabilities for evaluating the safety and performance of deep RL agents.
no code implementations • 17 Dec 2020 • Bettina Könighofer, Julian Rudolf, Alexander Palmisano, Martin Tappler, Roderick Bloem
The intuition behind online shielding is to compute during run-time the set of all states that could be reached in the near future.
Logic in Computer Science
no code implementations • 30 Jun 2020 • Roderick Bloem, Peter Gjøl Jensen, Bettina Könighofer, Kim Guldstrand Larsen, Florian Lorber, Alexander Palmisano
A timed pre-shield is placed before the system and provides a set of safe outputs.
no code implementations • 16 Jul 2018 • Nils Jansen, Bettina Könighofer, Sebastian Junges, Alexandru C. Serban, Roderick Bloem
This paper targets the efficient construction of a safety shield for decision making in scenarios that incorporate uncertainty.
1 code implementation • 29 Aug 2017 • Mohammed Alshiekh, Roderick Bloem, Ruediger Ehlers, Bettina Könighofer, Scott Niekum, Ufuk Topcu
In the first one, the shield acts each time the learning agent is about to make a decision and provides a list of safe actions.