Marc G. Bellemare
I lead the reinforcement learning efforts of the Google Brain team in Montréal, Canada. I am also a core industry member at Mila , where I advise graduate students. I obtained my PhD from the University of Alberta in Canada, proposing the use of Atari 2600 video games to benchmark progress in reinforcement learning research. My advisors were Michael Bowling and Joel Veness . In 2013–2017 I was a research scientist at DeepMind in the UK. Project highlights Distributional Reinforcement Learning MIT Press, Spr
As part of a collaboration with Loon , we used deep reinforcement learning to improve the navigation capabilities of stratospheric balloons. Based on a 13-balloon, 39-day controlled experiment over the Pacific Ocean, we found evidence of significantly improved power efficiency, increased time within range of a designated station, and determined that the controller had discovered new navigation techniques. Training the controller was made possible by a statistically plausible simulator that could model the w
Reincarnating RL
ICLR 2019 Task-Agnostic Reinforcement Learning Workshop
· Pierluca D'Oro
Nate Rahn
Lekan Molu
Philip Amortila
Marc G. Bellemare
Jesse Farebrother
Taylor Killian