Welcome to Northern Frontier, our video interview series that showcases in-depth and engaging conversations with some of the brightest academic minds in AI research today.
Edmonton, through the University of Alberta and the Alberta Machine Intelligence Institute, is considered the bedrock of Reinforcement Learning thanks to a critical mass of top researchers in the area. From Prof. Richard Sutton’s ground-breaking work to the Atari fields of Prof. Michael Bowling’s lab, this small but mighty city has helped put Canada on the map of world-leading AI research.
Last month, we took Prof. Balaraman Ravindran, professor of Reinforcement Learning at the Indian Institute of Technology at Madras and head of the school’s Robert Bosch Centre for Data Science and Artificial Intelligence, to a noisy arcade at a converted airport hangar just north of the city. In between Pac Man battles, we discussed why games are a crucial way to learn how to solve much bigger, more complex problems, the pros and cons of scalar rewards, and the natural link between RL and deep learning.