Marlos C. Machado

I am a research scientist at Google Brain in Montréal. I hold a Ph.D. from the University of Alberta where I worked with Michael Bowling and Marc G. Bellemare. My research interests lie broadly in Artificial Intelligence and particularly focus on Machine Learning/Reinforcement Learning.

[Google Scholar] [DBLP]

Marlos C. Machado

News

    • Dec: 2020: We had a paper accepted at Nature.
      • Autonomous Navigation of Stratospheric Balloons using Reinforcement Learning (w/ Bellemare, Candido, Castro, Gong, Moitra, Ponda, and Wang).
    • Sep: 2020: We had a paper accepted at NeurIPS’20.
      • An Operator View of Policy Gradient Methods (w/ Ghosh & Le Roux).
    • Aug: 2020: Our preprint is now available.
      • Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization (w/ Chung*, Thomas* & Le Roux).
    • Feb: 2020: I gave a talk at Stanford University.
      • Temporal Abstraction in RL with the Successor Representation.
    • Feb: 2020: I attended AAAI’20 in New York City.
    • Dec. 2019: We had two papers accepted at ICLR’20.
      • Exploration in Reinforcement Learning with Deep Covering Options (w/ Jinnai, Park, & Konidaris).
      • On Bonus Based Exploration Methods In The Arcade Learning Environment  (w/ Taiga, Fedus, Courville, & Bellemare).
    • Nov. 2019: We had a paper accepted at AAAI’20.
      • Count-Based Exploration with the Successor Representation (w/ Bellemare & Bowling).
    • Jul. 2019: I attended RLDM’19 in Montreal.
    • Mar. 2019: I started as a Research Scientist at Google Brain.

Blog Posts

Different behaviours for baselines that induce the same variance

The True Impact of Baselines in Policy Gradient Methods

Looking at Policy Gradient Methods from an Operators Perspective

Hello, world!