Agents operating in physical environments need to be able to handle dela...
Principled accountability for autonomous decision-making in uncertain
en...
Solving control tasks in complex environments automatically through lear...
Principled accountability in the aftermath of harms is essential to the
...
Besides the recent impressive results on reinforcement learning (RL), sa...
Safety is still one of the major research challenges in reinforcement
le...
Runtime enforcement refers to the theories, techniques, and tools for
en...
Evaluation of deep reinforcement learning (RL) is inherently challenging...
We present Tempest, a synthesis tool to automatically create
correct-by-...
In this paper, we propose a method to develop trustworthy reinforcement
...
This paper targets control problems that exhibit specific safety and
per...
Erroneous behaviour in safety critical real-time systems may inflict ser...
Shield synthesis is an approach to enforce a set of safety-critical
prop...
A prominent problem in artificial intelligence and machine learning is t...
Reinforcement learning algorithms discover policies that maximize reward...