Max Qiushi Lin

I am a PhD student in Computer Science at Simon Fraser University (SFU) , where I am fortunate to be advised by Sharan Vaswani.

Email: maxqslin at gmail dot com
[Google Scholar]     [Twitter]

Research

I am interested in machine learning and interactive decision making. My current research explores the theoretical foundations of reinforcement learning and the development of principled and implementable algorithms that enable agents to learn from experience. I am also engaged in optimization and statistics.

Papers

Optimistic Actor-Critic with Parametric Policies: Towards Bridging Theory and Practice
Max Qiushi Lin, Reza Asad, Kevin Tan, Haque Ishfaq, Csaba Szepesvári, Sharan Vaswani.
NeurIPS Workshop on Aligning Reinforcement Learning Experimentalists and Theorists (ARLET), 2025.

Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation
Max Qiushi Lin, Jincheng Mei, Matin Aghaei, Michael Lu, Bo Dai, Alekh Agarwal, Dale Schuurmans, Csaba Szepesvári, Sharan Vaswani.
Preprint, 2025.