I’m currently a Machine Learning Researcher at UBC affiliated with Vector Institute, working with Dr. Kelsey Allen @ UBC and Dr. Tom Silver @Princeton Univeristy. Before that, I completed my Master’s in Computer Science at the University of Alberta under the supervision of Dr. Levi Lelis.

I’m currently working on Programmatic Policies for Physical Strategy Learning. Broadly, my research asks: how can we build systems that learn, reason, and understand the world like humans? I explore this through the lens of symbolic reasoning and neurosymbolic AI, using tools from reinforcement learning and imitation learning.

You can contact me via zbashir1 AT ualberta DOT ca.

Publications

Plastic Programming Languages: Learning Neuro-Augmented Domain-Specific Languages
Zahra Bashir, David Aleixo, Kevin Ellis, Levi Lelis

SEGClobber - A Linear Clobber Solver
Taylor Folkerson, Zahra Bashir, Fatemeh Tavakoli, Martin Muller (International Computer Games Association)

Revisiting the Assessment of Programmatic Policy Interpretability: Insights from Human Evaluation
Zahra Bashir, Michael Bowling, Levi Lelis (Under Review)

LINT: Assessing the Interpretability of Programmatic Policies with Large Language Models
Zahra Bashir, Michael Bowling, Levi Lelis (RLC 2024 InterpPol Workshop)