Brandon Rozek

January 1, 0001


Computer Science / Data Science Research

Reinforcement Learning

Deep Reinforcement Learning: With Dr. Zacharski I focused more on a particular instance of Reinforcement Learning where deep neural networks are used. During this time, I built out a Reinforcement Learning library written in PyTorch. This library helps me have a test bed for trying out different algorithms and attempts to create my own.

Github Code

QEP Algorithm Slides

Reinforcement Learning: Currently studying the fundamentals of reinforcement learning with Dr. Davies. We went over the fundamentals such as value functions, policy functions, how we can describe our environment as a markov decision processes, etc.

Notes and Other Goodies

Github Code

Programming Languages

Programming Languages: Studying the design of programming languages. So far I made an implementation of the SLOTH programming language, experimenting with what I want my own programming language to be syntatically and paradigm wise.


Before this study, I worked though a book called “Build your own Lisp” and my implementation of a lisp like language is below.

Lispy Code


Competitive Programming: Studying algorithms and data structures necessary for competitive programming. Attending ACM ICPC in November with a team of two other students.

Math/Statistics Research

Worked on an independent study on the topic of Cluster Analysis. This is where you try to group similar observations without knowing what the labels are. I am studying under the guidance of Dr. Melody Denhere, the link below gives you more of a description of the project along with my course notes.

Cluster Analysis Spring 2018

Physics Research

For the two projects below, I worked on Quantum Research in a physics lab with a fellow student Hannah Killian and an advisor Dr. Hai Nguyen. I mostly assisted with the software support for the project and assisted in the mathematics in whatever way I can.

Modeling Population Dynamics of Incoherent and Coherent Excitation

Coherent Control of Atomic Population Using the Genetic Algorithm

In order to circumvent the frustrations I had with simulation code taking a while, I applied and received funding to build out a Beowulf cluster for the Physics department. Dr. Maia Magrakvilidze was the advisor for this project.

High Performance Cluster for Research and Education Report (nicknamed LUNA-C)

LUNA-C Poster