I am a Ph.D. candidate in Applied Mathematics and Statistics on the Statistics Track at Stony Brook University, with an expected graduation date of May 2027. My research focuses on reinforcement learning, statistical modeling, simulation, and sequential decision-making.
- Cumulative tic-tac-toe: First author of a peer-reviewed Stats article combining combinatorial game theory with temporal-difference reinforcement learning. Article · Official implementation
- RL-QESA: Co-first author of an AI for Math Workshop at ICML 2025 paper on reinforcement-learning-guided temperature control for simulated annealing. Paper · Publication page
- Reinforcement learning for blackjack: Co-first author of a manuscript in preparation comparing six reinforcement learning algorithms across progressively expanded action spaces, building on a 2025 pilot comparison of Monte Carlo control and proximal policy optimization.
I have also conducted a literature-based technical study of reinforcement learning for climate model parameterization and multiagent adaptation to sea-level rise.
Research methods: Markov decision processes, Monte Carlo methods, temporal-difference learning, deep Q-networks, proximal policy optimization, simulation, experimental design, statistical modeling, and time series analysis
Programming and research tools: Python, R, SQL, Gymnasium, Stable-Baselines3, Git and GitHub, and LaTeX
At Stony Brook University, I have taught or supported courses in mathematical statistics, statistical learning, time series, and statistical computing. My teaching has received two Excellence in Student Teaching awards, an Outstanding Student Teacher award, and two Teachers Rated Excellent Educators by their Students (TREES) recognitions.
I am interested in 2027 opportunities in reinforcement learning, machine learning, and data science where I can combine statistical rigor, computational research, and clear technical communication.