Marlos C. Machado, Ph.D.
Faculty of Science - Computing Science
Pronouns: He, Him, His
Personal Website: https://mcmachado.github.io/
Contact
Assistant Professor
Faculty of Science - Computing Science
- machado@ualberta.ca
Overview
Area of Study / Keywords
Artificial Intelligence Machine Learning Reinforcement Learning
About
Education
- B.Sc., Computer Science, Universidade Federal de Minas Gerais (UFMG), 2010
- M.Sc., Computer Science, Universidade Federal de Minas Gerais (UFMG), 2013
- Ph.D., Computing Science, University of Alberta, 2019
Research
Summary
Marlos C. Machado is an Assistant Professor at the University of Alberta, a Fellow of the Alberta Machine Intelligence Institute, a Canada CIFAR AI Chair, and a principal investigator of the Reinforcement Learning and Artificial Intelligence group. He served as a program co-chair of the 2025 Reinforcement Learning Conference and is one of the Editors-in-Chief of the Reinforcement Learning Journal. Before joining the University of Alberta, he spent four years as a research scientist at Google Brain and DeepMind. His work has been published in top venues in ML and AI, including Nature, JMLR, JAIR, NeurIPS, ICML, and ICLR. Among other contributions, he introduced stochasticity into the widely used Arcade Learning Environment, developed methods for temporally-extended exploration through options, and helped apply deep reinforcement learning to control Loon's stratospheric balloons. His research has been featured in popular media such as the BBC, Bloomberg TV, and Wired, and has received awards including the RLC 2025 Outstanding Paper Award on Theory of Reinforcement Learning, best paper honourable mentions at AISTATS and AAMAS, and selection for the AAAI 2025 New Faculty Highlights.
Courses
CMPUT 365 - Introduction to Reinforcement Learning
This course provides an introduction to reinforcement learning, which focuses on the study and design of learning agents that interact with a complex, uncertain world to achieve a goal. The course will cover multi- armed bandits, Markov decision processes, reinforcement learning, planning, and function approximation (online supervised learning). The course will take an information-processing approach to the study of intelligence and briefly touch on perspectives from psychology, neuroscience, and philosophy. The course will use the University of Alberta MOOC on Reinforcement Learning. Any student who understands the material in this course will understand the foundations of much of modern probabilistic artificial intelligence (AI) and be prepared to take more advanced courses, or to apply AI tools and ideas to real-world problems. Prerequisites: CMPUT 175 or 275; one of CMPUT 267, 466, or STAT 265.
CMPUT 499 - Topics in Computing Science
This topics course is designed for a one on one individual study course between a student and an instructor. Prerequisites for each section may differ and are defined by the instructor in the course outline.