Marlos Machado
Assistant Professor at University of Alberta
Edmonton, Alberta, Canada
Summary
🤩
Rockstar🎓
Top SchoolMarlos Machado is an Assistant Professor at the University of Alberta with 11 years of experience bridging foundational AI research and real-world reinforcement learning deployments. His work on representation learning, temporal abstraction, and exploration has led to high-impact contributions—such as eigenoptions and a deployed RL controller for stratospheric balloons—and publications in ICLR, ICML, NeurIPS and Nature. He combines deep theoretical insights (e.g., operator views of policy gradients and time-based uncertainty quantification) with practical engineering, including significant cleanup and modernization work on the widely used Arcade Learning Environment. A former researcher at DeepMind and Google, he mentors peers and emphasizes reproducibility and methodological best practices in empirical RL. Based in Edmonton, he brings a rare track record of moving ideas from proofs and benchmarks into live systems.
11 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of AlbertaBachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at Universidade Federal de Minas Gerais
English, Portuguese, Spanish
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (4)
cprogramming-language10
c-language10
refactoring10
makefile9
Programming languages (3)
Github contributions (5)
Farama-Foundation/Arcade-Learning-Environment
Feb 2015 - May 2019
A simple framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games
Role in this project:
Back-end Developer
Back-end DeveloperContributions:156 commits, 29 PRs, 22 pushes in 4 years 4 months
Contributions summary:Marlos primarily focused on refactoring and cleaning up the internal agent within the Arcade Learning Environment. Their work involved removing command-line flags and associated code related to the internal agent controller, player agents, and other related functionalities. Additionally, the user updated the manual to reflect the changes, streamlining the codebase. This cleanup included modifications to core files like `Settings.cxx`, `main.cpp`, `Defaults.cpp`, and makefiles, indicating a comprehensive effort.
ai-agent
mcmachado/options
Oct 2016 - Feb 2017
Contributions:70 commits, 44 pushes, 1 branch in 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.