Faisal Mohamed

فيصل محمد

Faisal Mohamed

ML Researcher · Mila & Université de Montréal

I am a research M.Sc student at Mila-Quebec AI Institute and Université de Montréal supervised by Glen Berseth.

I obtained my first master from the african master of machine intelligence program and I was supervised by Ben Eysenbach I spent sometime at the University of Tuebingen and the Max Planck Institute For Intelligent Systems. as part of the AIMS-Tübingen Fellowship Program Data Science & AI where I was fortunate to be mentored by Claudio Michaelis

My research goal is to develop deep RL algorithms that can be adapted efficiently in different environments and applied in a variety of domains. To reach this goal, I focus on self-supervised RL in both online and offline settings. I am also interested in probabilistic inference and representation learning for control.

Interests

  • Deep Reinforcement Learning
  • Representation Learning
  • Probablisitc Inference

Experience

  • Research Intern Oct 2023 - Sep 2024

    Mila-Quebec AI Institute

  • Teaching Assistant 2023

    African Institute for Mathematical Sciences, Senegal

  • Reseach Intern/Fellow 2022 - 2023

    University of Tübingen and Max Planck Institute For Intelligent Systems, Germany

  • Reseach Assistant 2019 - 2020

    Institute for Space Research and Aerospace, Sudan

  • Teaching Assistant 2018 - 2019

    University of Khartoum, Sudan

Publications

ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning
In International Conference on Learning Representations (ICLR), 2026
Roger Creus Castanyer, Faisal Mohamed, Pablo Samuel Castro, Cyrus Neary, Glen Berseth
Temporal representations for exploration: Learning complex exploratory behavior without extrinsic rewards
In International Conference on Learning Representations (ICLR), 2026
Faisal Mohamed, Cathrine Ji, Benjamin Eysenbach, Glen Berseth
Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning
RLC 2024
Adriana Hugessen*, Roger Creus Castanyer*, Faisal Mohamed*, Glen Berseth
An Empirical Investigation of Mutual Information Skill Learning
ALOE Workshop, ICLR 2022
Faisal Mohamed, Benjamin Eysenbach, Russ Salakhutdinov