-
![]()
Jan 22nd 2024
News
Such Great Heights: Marlos C. Machado shares his research at the Jasper Dark Sky Festival
Marlos C. Machado, Amii Fellow and Canada CIFAR AI Chair delivered his presentation "Flying Balloons in the Stratosphere of AI” at the Jasper Dark Festival, an annual festival celebrating solar wonder and stellar delights in Jasper National Park. Here Machado reflects on his experience at the festival, connects stratospheric balloons to space science, and reinforces the interdisciplinary nature of science.
Read more -
![]()
Feb 1st 2023
Research Post
Temporal Abstraction in Reinforcement Learning with the Successor Representation
Read this research paper, co-authored by Fellow & Canada CIFAR AI Chair at Russ Greiner: Towards artificial intelligence-based learning health system for population-level mortality prediction using electrocardiograms
Read more -
![]()
Jul 6th 2022
News
June 2022 AI Meetup Recap: Stratospheric Balloons
The June 2022 edition of AI Meetup was all about stratospheric balloons, featuring Amii’s Marlos C. Machado.
Read more -
![]()
Jul 13th 2021
News
Amii at ICML 2021: Accepted papers & workshops
The work of Amii researchers is being featured at the 38th annual International Conference on Machine Learning (ICML), running online this year from July 18 to 24.
Read more -
![]()
Jul 6th 2021
Research Post
A laplacian framework for option discovery in reinforcement learning
Read more -
![]()
Jun 9th 2021
News
AI talent in western Canada grows
Five new Canada CIFAR AI Chairs will advance fundamental AI research and boost industry innovation.
Read more -
![]()
Feb 19th 2021
Research Post
Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization
Read more -
![]()
Jan 29th 2021
News
AI Seminar Series 2021: Marlos C. Machado, Autonomous Navigation of Stratospheric Balloons using reinforcement learning
On January 22, 2021, DeepMind Alberta research scientist Marlos C. Machado presented on autonomous navigation of stratospheric balloons using reinforcement learning.
Read more -
![]()
Dec 14th 2020
News
AI Seminar Series 2020: Marlos C. Machado, An operator view of policy gradient methods
On Nov 27, 2020, research scientist at Google Brain (Montreal) and Amii alumnus Marlos C. Machado presented “An operator view of policy gradient methods”
Read more -
![]()
Dec 1st 2020
Research Post
Autonomous navigation of stratospheric balloons using reinforcement learning
Read more -
![]()
Jan 1st 2018
Research Post
Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
Read more -
![]()
Dec 26th 2016
News
The Success of DQN Explained by “Shallow” Reinforcement Learning
This post examines the principles underlying DQN’s impressive performance by introducing a fixed linear representation that achieves DQN-level performance in the Arcade Learning Environment.
Read more
