An Intentional Forgetting-Driven Self-Healing Method For Deep Reinforcement Learning Systems

1 code implementation • 23 Aug 2023 • Ahmed Haj Yahmed, Rached Bouchoucha, Houssem Ben Braiek, Foutse khomh

Dr. DRL successfully helps agents to adapt to 19. 63% of drifted environments left unsolved by vanilla CL while maintaining and even enhancing by up to 45% the obtained rewards for drifted environments that are resolved by both approaches.

Continual Learning reinforcement-learning

Quality Issues in Machine Learning Software Systems

1 code implementation • 26 Jun 2023 • Pierre-Olivier Côté, Amin Nikanjam, Rached Bouchoucha, Ilan Basta, Mouna Abidi, Foutse khomh

We validate the identified quality issues via a survey with ML practitioners.

Can Ensembling Pre-processing Algorithms Lead to Better Machine Learning Fairness?

no code implementations • 5 Dec 2022 • Khaled Badran, Pierre-Olivier Côté, Amanda Kolopanis, Rached Bouchoucha, Antonio Collante, Diego Elias Costa, Emad Shihab, Foutse khomh

As machine learning (ML) systems get adopted in more critical areas, it has become increasingly crucial to address the bias that could occur in these systems.

Fairness

Quality issues in Machine Learning Software Systems

1 code implementation • 18 Aug 2022 • Pierre-Olivier Côté, Amin Nikanjam, Rached Bouchoucha, Foutse khomh

This empirical study aims to identify a catalog of bad-practices related to poor quality in MLSSs.