The 16th annual CIFAR Deep Learning + Reinforcement Learning (DLRL) Summer School takes place this week, from August 3 to 7. Every year, DLRL brings together graduate students, post-docs and professionals to cover the foundational research, new developments, and real-world applications of deep learning and reinforcement learning.
The event is co-hosted in rotation by Canada’s three national AI institutes: Amii, Mila and the Vector Institute. As the 2020 Host Institute, Mila is working with CIFAR to bring the event online for over 300 students from across 45 countries.
Amii’s involvement as a supporting institute includes:
Talks by Amii Fellows
Rupam Mahmood speaks on robotics, providing a first-principles approach of thinking about industrial applications and human progress that naturally leads to what we know of as reinforcement learning. He describes some of the pitfalls that lead to misunderstandings and failed utilization of this technology, as well as recent advances of reinforcement learning in industrial applications, significant blockers, and how to navigate this new territory of applications.
Adam White’s lecture provides an introduction to reinforcement learning and intelligence, which focuses on the study and design of agents that interact with a complex, uncertain world to achieve a goal. With an emphasis on agents that can make near-optimal decisions in a timely manner with incomplete information and limited computational resources, the lecture covers Markov decision processes, reinforcement learning and function approximation (online supervised learning).
AI Improv
As part of DLRL’s social events, Amii is hosting an online evening of tech-infused improvised theatre and comedy. Improbotics features co-creators Piotr Mirowski and Amii alum Kory Matthewson alongside Edmonton’s Rapid Fire Theatre and the world’s first artificial improviser, A.L.Ex. (the Artificial Language Experiment). A.L.Ex. “performs” in the show, becoming one of the troupe as it sends its lines to one of the improvisers via an earpiece. The performer then attempts to physically and emotionally justify AI-generated lines that hopefully make sense. Each performance draws suggestions from the audience, making every show one of a kind. Improbotics has been featured in the New York Times, Wall Street Journal, New Scientist, RTÉ One, Global News Canada and Bloomberg.
Visit the DLRL website for more information on this year’s event.
Check out the highlights from last year’s DLRL Summer School in Edmonton, co-hosted by Amii: