Nadeem Ward

Master’s Student at Mila/McGill. Passionate about AI.

About me

I’m a second year Master’s student at Mila and the Reasoning and Learning Lab at McGill University where I work on Reinforcement Learning under the supervision of Prof. Doina Precup. I also hold a Bachelors degree in Mathematics and Software Engineering from McGill University.

My research interests are broadly focused on getting agents to make “optimal” decisions in complex environements (whatever we decide “optimal” means). This leads me to work at the intersection of Reinforcement Learning and Deep Learning.

I’m always interested in learning new things and talking to people about machine learning in general, feel free to reach out if you want to chat!

LinkedIn  linkedin Github  github Twitter  Google Scholar  icon-googlescholar CV

Project Highlights

ICML 2019 workshop paper


Some work done at Mila presented at an ICML workshop.

Lectures given at McGill on introductory topics in Reinforcement learning


Tutorials on introductory Reinforcement Learning topics as part of my Lectures for a course at McGill taught to Master students in the Management department.

Implementation of basic policy gradient algorithms used in Reinforcement Learning


Reimplementation of REINFORCE and one-step Actor-Critic with and without a baseline network in pytorch.