Revan MacQueen

Reinforcement Learning · Game Theory · Multi-agent Systems

Hello! I am an ML Engineer at RLCore Technologies, working on developing RL agents for process control. Previously I was an ML Resident at Alberta Machine Intelligence Institute (Amii), where I developed and deployed a reinforcement learning agent to autonomously control a mobile water treatment plant.

I completed my master's at the University of Alberta and Amii, supervised by James R. Wright. My thesis received the departmental Outstanding MSc. Thesis Award. Before that, I completed my BSc in Honours Computing Science at the University of Alberta.

My research interests are reinforcement learning, algorithmic game theory, and multi-agent systems. I'm particularly interested in algorithms that learn through self-play in strategic settings, and the theoretical guarantees that can be established for such methods. Here are technical and general audience summaries of my thesis work.

Outside of research, one of my hobbies is photography. Check out some of my photos here.

Publications & Preprints

5

Approximating Nash Equilibria in General-Sum Games via Meta-Learning

David Sychrovský, Christopher Solinas, Revan MacQueen, Kevin Wang, James R. Wright, Nathan R. Sturtevant, Michael Bowling

AAMAS 2026

3

Resmax: An Alternative Soft-Greedy Operator for Reinforcement Learning

Erfan Miahi, Revan MacQueen, Alex Ayoub, Abbas Masoumzadeh, Martha White

Transactions on Machine Learning Research 2023

2

Finding an Optimal Set of Static Analyzers To Detect Software Vulnerabilities

Jiaqi He, Revan MacQueen, Natalie Bombardieri, Karim Ali, James R. Wright, Cristina Cifuentes

IEEE ICSME 2023

1

Game Theoretic Malware Detection

Revan MacQueen, Natalie Bombardieri, James R. Wright, Karim Ali

arXiv preprint 2020

Research Experience

Graduate Research Assistantship Fellowship 2021–2023

University of Alberta & Amii · Supervisor: Dr. James R. Wright

Researched self-play convergence in non-zero-sum multiplayer games; proved novel guarantees via polymatrix decomposability. Published at NeurIPS 2023.

Machine Learning Intern Sep. 2021–Jan. 2022

Amii · Supervisor: Talat Iqbal

Implemented an RL-based hyperparameter tuning system for transformer models with an industrial client. Client feedback: "this partnership is a huge success and substantial progress has been made in demonstrating the potential of using RL."

Research Assistant May–Sep. 2020

University of Alberta · Supervisors: Dr. James R. Wright & Dr. Karim Ali

Developed a game-theoretic model of malware detection and applied it to find optimal detection strategies.

Presentations

Game Theoretic Malware Detection

Presented to Oracle Labs Australia

Fixing Neural Networks with Solver-Aided Languages

Poster presentation, ACM SIGPLAN (SPLASH)

Teaching Experience

Machine Learning Facilitator (WILO) Nov. 2022–Mar. 2023

Amii

Delivered Amii's introductory ML course, ML Foundations, to professional and academic audiences.

Program Delivery Support – Facilitation (WILO) Nov. 2022–Mar. 2023

Amii

Breakout room facilitator for the Canadian Information Office Strategy Council's Ethics Workshop.

Teaching Assistant – CMPUT 412: Experimental Mobile Robotics Jan.–Dec. 2022

University of Alberta · Supervisor: Dr. Matthew Taylor

Developed course content and helped instruct senior robotics class.

First People's House Tutor 2022

University of Alberta

Provided one-on-one support to undergraduate computing science students.

Teaching Assistant – CMPUT 366: Intelligent Systems Jan.–Dec. 2021

University of Alberta · Supervisor: Dr. James R. Wright

Helped instruct artificial intelligence survey class.

Students Union Tutor 2019–2020

University of Alberta

Tutored undergraduate computing science students.