Search Results for author: Filip Cano Córdoba

Found 3 papers, 2 papers with code

Safety Shielding under Delayed Observation

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.

Autonomous Driving

Paper
Code

Analyzing Intentional Behavior in Autonomous Agents under Uncertainty

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.

counterfactual Counterfactual Reasoning +1

Paper
Code

Search-Based Testing of Reinforcement Learning

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.

reinforcement-learning Reinforcement Learning (RL)

Paper
Add Code

Cannot find the paper you are looking for? You can Submit a new open access paper.