Hello,
I'm Peter. I'm a researcher at NVIDIA.

Learn More

About Me

Who Am I?

Hello! I'm Peter Xenopoulos.

I'm a senior research scientist at NVIDIA, exploring the ways humans engage with computers in contexts like work and games. I am particularly focused on human performance and experience in those domains. You can see my profile on NVIDIA Research for more.

I have also worked substantially in sports, including quantitative research for a sports betting exchange, a player investment fund, and a professional baseball team. I also maintain many open source projects in esports analytics that have thousands of installations.

My ResearchDownload CV

FAQ

Zee-naw-pu-lus
Work and games are high-performance environments where humans are often operating at their peak. We also happen to spend a huge amount of our time on these activities! They involve mastery, communication, and training, and the data produced in these environments is deeply interesting.
It's important to work on projects you enjoy. I started a few projects as a student that not only improved my coding ability but also brought me in contact with people who were nice enough to help me along the way. Find what you like and work on that -- it will come much easier.
  • Boon — A Deadlock demo/replay parser
  • Awpy — A Counter-Strike 2 demo/replay parser
  • ESTA — A large dataset of professional esports trajectories and actions
  • Litebook — A fast limit order book in Python+Rust
Find a recent paper of mine, and you'll see an email. Otherwise, check the Boon Discord.

Research

Research Areas

Human Performance

I study how humans perform at their peak in work and play. From mastery and decision-making to communication and training, I seek to measure, model, and improve human performance and experience.

AI & Machine Learning

My work is driven by large-scale behavioral data, from spatiotemporal tracking and event logs to video, text, and audio. I focus on building interpretable and performant models that surface actionable insights.

Games, Esports & Sports

Competitive environments — from video games to professional sports — are where I apply my research. I've worked across esports titles like Counter-Strike and Deadlock, as well as baseball, basketball, American football, ice hockey, and soccer.

Open Source Tooling

I maintain several open source projects with thousands of installations, including demo parsers, analytics libraries, and datasets. I believe in building tools that empower the broader research and developer community. Check out my open source repositories.

Tools & Data

Tools & Data

Boon  Link

pip install boon-deadlock

Boon is a project to create tooling to parse and analyze Deadlock demos/replay files. It contains a core Rust parser, a Python library that provides bindings to the parser, and a command-line interface application.

Awpy  Link

pip install awpy

Awpy is a Python library to parse, analyze and visualize Counter-Strike 2 demofiles. Since its release, Awpy has roughly 100,000 installations, and has an active Discord community. The library is well-documented and works on Google Colab.

Esports Trajectories and Actions (ESTA)  Link

git clone https://github.com/pnxenopoulos/esta

The ESTA dataset contains about 1.5k parsed CSGO demofiles using awpy. ESTA contains detailed spatiotemporal data on player actions (damages, kills, grenade throws, etc.) and trajectories. In total, ESTA is about 4 GB of compressed JSONs and contains 8.6m million actions and 7.9m game frames.

Litebook  Link

pip install litebook

Litebook is a fast and performant limit order book in Python utilizing a Rust backend.