Guy Leroy

Hi! My name is Guy Leroy and I am currently a Machine Learning Engineer at TikTok focusing on spam, bots, and fake engagement prevention as part of the BRIC Risk Systems ML foundation team. Previously, I was an Associate Researcher at Microsoft Research, working in the Deep Reinforcement Learning for Games team. I graduated from Imperial College London with an MEng in Mathematics & Computer Science. My Master's thesis was titled Multi-agent Deep Reinforcement Learning for Anatomical Landmark Detection, and supervised by Dr. A. Alansary and Prof. D. Rueckert.

Experience

TikTok

Machine Learning Engineer

Focusing on spam, bots, and fake engagement prevention as part of the BRIC Risk Systems ML foundation team.

Microsoft Research

Associate Researcher

Working in the Deep Reinforcement Learning for Games team focusing on multi-agent collaboration.

Designed and integrated state-of-the-art Deep Reinforcement Learning solutions to AAA games.
Co-authored "Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation" at ICML '21.
Published “How Humans Perceive Human-like Behavior in Video Game Navigation” at CHI '22.
Speaker at GDC AI Summit '22 on “Age of Empires IV: Machine Learning Trials and Tribulations”.

Avanade

Solution Dev Intern

Avanade, joint venture between Microsoft and Accenture, provides IT consulting and services focused on the Microsoft ecosystem.

Built robots with UiPath to speed up processes from 30min to 30s.
Scaled Intelligent Automation's robots by deploying web app and VM on Azure.
Won client GRDF's hackathon by automating resolution of low value-added support tickets (about 65 actions per ticket resolution, for ~30 tickets each day).

Blockchain and Crypto-technologies society of ICL

Co-founder and Secretary

Two friends and I wanted to attend talks and workshops about blockchain technologies. We realised Imperial College was missing such society, so we decided to create it.

Operated the stand at Imperial Fresher’s Fair and gathered 300+ subscriptions.
Organised workshops and talks (with speakers working in the blockchain ecosystem and researchers).
Formed a partnership with London Blockchain Labs which led to more talks and workshops.

Prof. Kevin Buzzard & Imperial College London

Research Assistant in Automated Theorem Proving

Research in computer science at Imperial College London to automate proofs in number theory using the Lean Theorem Prover supervised by Prof. Kevin Buzzard. Open source project available on GitHub.

Mercuris Conseil

Front-End Developer Intern

Mercuris Conseil is a startup specialised in developing web solutions for small and medium size businesses.

Automated websites building processes using Drupal.
Built an e-commerce website for a client.

Projects & Publications

Naval battles in Age of Empires IV

In this project in collaboration with World's Edge studio, we train Multi-Agent Reinforcement Learning (RL) naval units in Age of Empires IV . The aim, unlike related work, is not to reach superhuman performances and beat the top players. The aim is to build a more immersive and enjoyable experience for the players by creating more human-like opponents. This work was presented at GDC AI summit '22, “Age of Empires IV: Machine Learning Trials and Tribulations”. My co-speaker Peter Chan speaks about how battle outcomes are predicted using supervised learning. Disclaimer: the RL naval units are not in the released version of the game.

View talk (requires GDC subscription)

How Humans Perceive Human-like Behavior in Video Game Navigation

How well do people assess human-likeness in human- and AI-generated behavior? We present a qualitative study of hundreds of crowd-sourced assessments of human-likeness of behavior in a 3D video game navigation task. We focus on an AI agent that has passed a Navigation Turing Test. We give insights on the characteristics that people consider as human-like. Understanding these characteristics is a key first step for improving AI agents in the future.

CHI '22 publication

Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation

A key challenge on the path to developing agents that learn complex human-like behavior is the need to quickly and accurately quantify human-likeness. We present an automated Navigation Turing Test. We demonstrate the effectiveness of our automated NTT on a navigation task in a complex 3D environment. Our best models achieve high accuracy when distinguishing true human and agent behavior.

ICML '21 publication

Multi-agent Deep Reinforcement Learning for Anatomical Landmark Detection

My Master's thesis, supervised by Dr. Amir Alansary and Prof. Daniel Rueckert, achieves state-of-the-art accuracy in anatomical landmark detection. we explored approaches involving multiple cooperating agents with a focus on their communication in order to improve performances. The work was subsequently published in the MICCAI 2020 MLCN workshop. You can also read the original report here.

MICCAI MLCN '20 publication

View on Github

Tennis with Machine Learning and Computer Vision

Integrated court detection, ball tracking, and multi-person pose estimation to gather metrics on tennis players such as step count, shot hit map, ball speed and shot types, in Java in a team of 5.

View demo

View report