Manfred Diaz

Ph. D candidate at Mila and Montreal Robotics.

prof_pic.jpg

 Montreal, QC, Canada

I am a final year PhD student in Machine Learning and Robotics at Mila under the supervision of Liam Paull with focus on curriculum and generalization in reinforcement learning. I have interned at J.P. Morgan AI Research, Motional Inc., and Huawei Noah’s Ark Lab Canada.

Earlier, I graduated from Concordia University with an M.Sc. in Computer Science under Thomas Fevens. Simultaneously, I spent a year as a visiting researcher in the Shared Reality Lab at McGill University under the supervision of Jeremy Cooperstock. Before, I completed a B.Sc. in Computer Science with summa cum laude from Universidad de las Ciencias Informaticas in Havana, Cuba.

News
Jul 29, 2022 I gave an invited talk on Generalization Games for RL at Berkeley MALS and Mila RL Sofa. Access the recording here.
Jun 20, 2022 I started as a Research Intern at J. P. Morgan AI Research in London!
Mar 28, 2022 Our paper Generalization Games for Reinforcement Learning has been accepted for presentation at ICLR workshop on Gamification and Multiagent Solutions.
Selected Publications
  1. Generalization Games for Reinforcement Learning
    Manfred Diaz, Charlie Gauthier, Glen Berseth, and Liam Paull
    2022
  2. Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization
    Shixiang Shane GuManfred Diaz, Daniel C. Freeman, Hiroki Furuta, and 6 more authors
    2021
  3. Active Domain Randomization
    Bhairav MehtaManfred Diaz, Florian Golemo, Christopher J. Pal, and 1 more author
    2020
  4. To Veer or Not to Veer: Learning From Experts How to Stay Within the Crosswalk
    Manfred Diaz, Roger Girgis, Thomas Fevens, and Jeremy Cooperstock
    Oct 2017