Intro to Deep Reinforcement Learning, or How to Beat Humans at Video Games

Bogdan Mazoure

12:00, Friday, Nov. 30
BURN 1025



Do you want to win all your Fortnite matches while working on your thesis? Don't worry! With very little math and some Python code, a deep reinforcement learning (DRL) agent can do that for you. Deep RL is concerned with finding optimal actions in decision processes using primitive inputs such as pixels on your computer screen. RL has seen successful applications in healthcare, robotics, and game-playing; if your problem has a defined notion of reward over time, then you could also formulate it as an RL task.

All graduate students are invited. As with all talks in the graduate student seminar, this talk will be accessible to all graduate students in math and stats.

This seminar was made possible by funding from the McGill mathematics and statistics department and PGSS.

back