2 papers
cs.LG2025
Zero-Incentive Dynamics: a look at reward sparsity through the lens of unrewarded subgoals
Yannick Molinghen, Tom Lenaerts
This work re-examines the commonly held assumption that the frequency of rewards is a reliable measure of task difficulty in reinforcement learning. We identify and formalize a str…
cs.LG2025
FRAUD-RLA: A new reinforcement learning adversarial attack against credit card fraud detection
Daniele Lunghi, Yannick Molinghen, Alkis Simitsis +2
Adversarial attacks pose a significant threat to data-driven systems, and researchers have spent considerable resources studying them. Despite its economic relevance, this trend la…