Filip Cano Córdoba — accepted AI-conference papers

2023

Analyzing Intentional Behavior in Autonomous Agents under Uncertainty

Filip Cano Córdoba, Samuel Judson, Timos Antonopoulos, Katrine Bjørner, Nicholas Shoemaker, Scott J. Shapiro +2

IJCAI 2023poster

Principled accountability for autonomous decision-making in uncertain environments requires distinguishing intentional outcomes from negligent designs from actual accidents. We propose analyzing the behavior of autonomous agents through a quantitative measure of the evidence of intentional behavior.…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2022

Search-Based Testing of Reinforcement Learning

Martin Tappler, Filip Cano Córdoba, Bernhard K. Aichernig, Bettina Könighofer

IJCAI 2022poster

Evaluation of deep reinforcement learning (RL) is inherently challenging. Especially the opaqueness of learned policies and the stochastic nature of both agents and environments make testing the behavior of deep RL agents difficult. We present a search-based testing framework that enables a wide ran…

Cited by 26 Source ↗PDF ↗Scholar ↗