Skip to content
CIFAR header logo
fr
menu_mobile_logo_alt
  • News
  • Events
    • Public Events
    • Invitation-only Meetings
  • Programs
    • Research Programs
    • Pan-Canadian AI Strategy
    • Next Generation Initiatives
    • Global Call for Ideas
  • People
    • Fellows & Advisors
    • CIFAR Azrieli Global Scholars
    • Canada CIFAR AI Chairs
    • AI Strategy Leadership
    • Solution Network Members
    • Leadership
  • Support Us
  • About
    • Our Story
    • CIFAR 40
    • Awards
    • Partnerships
    • Publications & Reports
    • Careers
    • Staff Directory
    • Equity, Diversity & Inclusion
  • fr
  • Home
  • Bio

Follow Us

Marlos C. Machado

Marlos C. Machado

Appointment

Canada CIFAR AI Chair

Pan-Canadian AI Strategy

Connect

Website

About

Marlos’s research focuses on designing algorithms that discover spatial and temporal abstractions in order to empower reinforcement learning (RL) agents to tackle the problems of credit-assignment, exploration, and generalization. For space abstractions, he has shown the benefits of incorporating the sequential structure of decision making problems into the representation learning process, as well as the benefits of augmenting agents’ representations with predictions and uncertainty estimates. For temporal abstractions, Marlos has introduced the idea of using learned representations to discover options (i.e., courses of actions) for temporally extended exploration. Several of these ideas were incorporated in the design of a deep RL algorithm for controlling balloons in the stratosphere; one of the first deployments of deep RL in the real-world. Marlos is also passionate about reproducibility and proper experimentation in machine learning; he was responsible for introducing stochasticity and modes to the widely popular Arcade Learning Environment.

Relevant Publications

  • Agarwal, R., Machado, M. C., Castro, P., Bellemare, M. (2021) Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning. International Conference on Learning Representations (ICLR).

  • Ghosh, D., Machado, M.C., Le Roux, N. (2020). An Operator View of Policy Gradient Methods. Neural Information Processing Systems (NeurIPS).

  • Bellemare, M., Candido, S., Castro, P., Gong, J., Machado, M. C., Moitra, S., Ponda, S., & Wang, Z. (2020). Autonomous Navigation of Stratospheric Balloons using Reinforcement Learning. Nature; 588:77‑82.

  • Machado, M. C., Rosenbaum, C., Guo, X., Liu, M., Tesauro, G., Campbell, M. (2018). Eigenoption Discovery through the Deep Successor Representation. International Conference on Learning Representations (ICLR).

  • Machado, M. C., Bellemare, M., Talvitie, E., Veness, J., Hausknecht, M., Bowling, M. (2018). Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents. Journal of Artificial Intelligence Research 61: 523‑562.

Institution

Amii

University of Alberta

Department

Department of Computing Science

Education

  • PhD (Computing Science), University of Alberta
  • MSc (Computer Science), Universidade Federal de Minas Gerais (UFMG)
  • BSc (Computer Science), Universidade Federal de Minas Gerais (UFMG)

Country

Canada

Support Us

CIFAR is a registered charitable organization supported by the governments of Canada, Alberta and Quebec, as well as foundations, individuals, corporations and Canadian and international partner organizations.

Donate Now
CIFAR header logo

MaRS Centre, West Tower
661 University Ave., Suite 505
Toronto, ON M5G 1M1 Canada

Contact Us
Media
Careers
Accessibility Policies
Supporters
Financial Reports
Subscribe

  • © Copyright 2023 CIFAR. All Rights Reserved.
  • Charitable Registration Number: 11921 9251 RR0001
  • Terms of Use
  • Privacy
  • Sitemap

Subscribe

Stay up to date on news & ideas from CIFAR.

This website stores cookies on your computer. These cookies are used to collect information about how you interact with our website and allow us to remember you. We use this information in order to improve and customize your browsing experience and for analytics and metrics about our visitors both on this website and other media. To find out more about the cookies we use, see our Privacy Policy.
Accept Learn more