Flag indicating the English language is selected

Hi, I'm a first year PhD Student at the University of Michigan Ann Arbor, where I'm a member of the Strategic Reasoning Group in the AI Lab at Michigan. I am extremely fortunate to be advised by Prof. Michael Wellman.

For undergrad I attended Lafayette College graduating in 2021. After Lafayette I was working full time and attending Tufts University to pursue my MS in Computer Science, where I had a great experience, got to work on interesting research, and met many great people who allowed me to be a student while I worked in industry; I graduated from Tufts in 2024.

Summer 2024 I worked as a research intern for the Air Force Research Lab (AFRL). I collaborated with the AI & Autonomous Decision Making Group and the Control Science Center, where I worked on differential game theory & pursuit-evasion games, GNNs, and graph theory. I was hosted by Dr. Scott Nivison.

I spent 2.5 years right out of college in industry where I worked as a software engineer at Capital One working on their Low Latency Data Store team and software for real time credit card fraud detection. I also spent time at Jefferies working as a Quantitative Researcher in fixed income.

Broad Research Interests

Multi-Agent Systems, Economics and Computation, Reinforcement Learning, and Mathematical-Economics & Finance.

Some mementos from my days as a D1 athlete

While at Lafayette I played 4 years of division 1 lacrosse. I was also awarded the David Heard award by the Athletic Department at Lafayette College. I was fortunate to play with some of the best players and coaches in the world and make some great memories.

Memento 1
Memento 2
Memento 3
Memento 4

Fast and the Furios: Hot Starts in Pursuit Evasion Differential Games

Abstract: Effectively positioning pursuers in pursuit-evasion games without prior knowledge of evader locations remains a significant challenge. A novel approach that combines game-theoretic control theory with Graph Neural Networks is introduced in this work. By conceptualizing pursuer configurations as strategic arrangements and representing them as graphs, a Graph Characteristic Space is constructed via multi-objective optimization to identify Pareto-optimal configurations. A Graph Convolutional Network (GCN) is trained on these Pareto-optimal graphs to generate strategically effective initial configurations, termed \textit{hot starts}. Empirical evaluations demonstrate that the GCN-generated hot starts provide a significant advantage over random configurations. In scenarios considering multiple pursuers and evaders, this method hastens the decline in evader survival rates, reduces pursuer travel distances, and enhances containment, showcasing clear strategic benefits.

Quantal Response-Based Defense in One vs. Many Stackelberg Security Games

Spent 2023-2024 School year researching Stackelberg Security Games and Deception. Worked to find reductions from Stackelberg Security Games to social planner problems in macroeconomic models.

Understanding Eviction Rates Enduced by COVID, a Statistical, Mechanism Design, and Game Theoretic Perspective

Spent 2021 School year researching the impacts of COVID-19 to the renting market in Pennsylvania and Easton. I took an approach through statistics, econometrics, mechanism design, and game theory. I worked with the city of Easton to help implement these Mechanism Design solutions.