I am Ishaq Hamza, an Operations Research PhD student at the Edwardson School of Industrial Engineering, Purdue University, working with Dr. Zaiwei Chen.
My long-term goal is to advance artificial general intelligence (AGI) through reinforcement learning (RL), extending RL beyond conventional applications and modeling assumptions. I develop and analyze practical algorithms for decision-making in stochastic environments, with a focus on understanding their behavior and performance under realistic assumptions. I aim for theoretical guarantees that provide practical insight and analytical techniques that extend to broader problems in machine learning and decision-making.
I really like to make sense of random stuff. While my work is mostly theoretical, I like to explore applications where decision problems in nuanced, and perhaps noisy, stochastic environments show up naturally. I also love to discuss ideas in a way that blurs the boundary between formal discussion and casual talk.
MLxOR Workshop, NeurIPS 2026
To be updated.
A graduate course taken by PhD students, which I assisted during the third year of my undergraduate studies. I conducted tutorials, answered students’ questions, and graded assignments. The course covered rigorous convex analysis in extended-real settings and the operator-theoretic treatment of optimization algorithms in both smooth and non-smooth settings, using set-valued analysis for proximal algorithms.
Loading the CV…