Guaranteeing Reproducibility in Deep Learning Competitions

Brandon Houghton, Stephanie Milani, Nicholay Topin, William H. Guss, Katja Hofmann, Diego Perez Liebana, Manuela Veloso, Ruslan Salakhutdinov

Abstract: To encourage the development of methods with reproducible and robust training behavior, we propose a challenge paradigm where competitors are evaluated directly on the performance of their learning procedures rather than pre-trained agents. Since competition organizers re-train proposed methods in a controlled setting they can guarantee reproducibility, and -- by retraining submissions using a held-out test set -- help ensure generalization past the environments on which they were trained.