27 citations · 52 across the 11 of their papers we have counts for
15 papers
Easy-to-Use Shielding for Reinforcement Learning
Stefan Pranger, Bettina Könighofer
Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their environment. Safe exploration is…
Safety Shielding under Delayed Observation
Filip Cano Córdoba, Alexander Palmisano, Martin Fränzle +2
Agents operating in physical environments need to be able to handle delays in the input and output signals since neither data transmission nor sensing or actuating the environment…
Analyzing Intentional Behavior in Autonomous Agents under Uncertainty
Filip Cano Córdoba, Samuel Judson, Timos Antonopoulos +5
Principled accountability for autonomous decision-making in uncertain environments requires distinguishing intentional outcomes from negligent designs from actual accidents. We pro…
Learning Environment Models with Continuous Stochastic Dynamics
Martin Tappler, Edi Muškardin, Bernhard K. Aichernig +1
Solving control tasks in complex environments automatically through learning offers great potential. While contemporary techniques from deep reinforcement learning (DRL) provide ef…
'Put the Car on the Stand': SMT-based Oracles for Investigating Decisions
Samuel Judson, Matthew Elacqua, Filip Cano +4
Principled accountability in the aftermath of harms is essential to the trustworthy design and governance of algorithmic decision making. Legal theory offers a paramount method for…
Online Shielding for Reinforcement Learning
Bettina Könighofer, Julian Rudolf, Alexander Palmisano +2
Besides the recent impressive results on reinforcement learning (RL), safety is still one of the major research challenges in RL. RL is a machine-learning approach to determine nea…
Correct-by-Construction Runtime Enforcement in AI -- A Survey
Bettina Könighofer, Roderick Bloem, Rüdiger Ehlers +1
Runtime enforcement refers to the theories, techniques, and tools for enforcing correct behavior with respect to a formal specification of systems at runtime. In this paper, we are…
TEMPEST -- Synthesis Tool for Reactive Systems and Shields in Probabilistic Environments
Stefan Pranger, Bettina Könighofer, Lukas Posch +1
We present Tempest, a synthesis tool to automatically create correct-by-construction reactive systems and shields from qualitative or quantitative specifications in probabilistic e…
Online Shielding for Stochastic Systems
Bettina Könighofer, Julian Rudolf, Alexander Palmisano +2
In this paper, we propose a method to develop trustworthy reinforcement learning systems. To ensure safety especially during exploration, we automatically synthesize a correct-by-c…
Adaptive Shielding under Uncertainty
Stefan Pranger, Bettina Könighofer, Martin Tappler +3
This paper targets control problems that exhibit specific safety and performance requirements. In particular, the aim is to ensure that an agent, operating under uncertainty, will…
Synthesis of Admissible Shields
Laura Humphrey, Bettina Könighofer, Robert Könighofer +1
Shield synthesis is an approach to enforce a set of safety-critical properties of a reactive system at runtime. A shield monitors the system and corrects any erroneous output value…
Safe Reinforcement Learning via Shielding
Mohammed Alshiekh, Roderick Bloem, Ruediger Ehlers +3
Reinforcement learning algorithms discover policies that maximize reward, but do not necessarily guarantee safety during learning or execution phases. We introduce a new approach t…
Shield Synthesis: Runtime Enforcement for Reactive Systems
Roderick Bloem, Bettina Koenighofer, Robert Koenighofer +1
Scalability issues may prevent users from verifying critical properties of a complex hardware design. In this situation, we propose to synthesize a "safety shield" that is attached…
Synthesizing Multiple Boolean Functions using Interpolation on a Single Proof
Georg Hofferek, Ashutosh Gupta, Bettina Könighofer +2
It is often difficult to correctly implement a Boolean controller for a complex system, especially when concurrency is involved. Yet, it may be easy to formally specify a controlle…
Synthesizing Robust Systems with RATSY
Roderick Bloem, Hans-Jürgen Gamauf, Georg Hofferek +2
Specifications for reactive systems often consist of environment assumptions and system guarantees. An implementation should not only be correct, but also robust in the sense that…