3 papers
cs.AI2026
The Shift Toward Open and Reproducible AI Research
Kevin L Coakley, Thijs Snelleman, Holger Hoos +1
The reproducibility crisis has directed the AI research community toward improving documentation practices. Several studies have identified methodological issues, and in response,…
cs.CY2025
Automated Reproducibility Has a Problem Statement Problem
Thijs Snelleman, Peter Lundestad Lawrence, Holger H. Hoos +1
Background. Reproducibility is essential to the scientific method, but reproduction is often a laborious task. Recent works have attempted to automate this process and relieve rese…
cs.LG2024
Combining Automated Optimisation of Hyperparameters and Reward Shape
Julian Dierkes, Emma Cramer, Holger H. Hoos +1
There has been significant progress in deep reinforcement learning (RL) in recent years. Nevertheless, finding suitable hyperparameter configurations and reward functions remains c…