Reinforcement learning (RL) is a branch of machine learning in which an agent interacts with an environment in order to maximize a specified reward. Industrial applications of reinforcement learning have so far been limited, but with recent advances in deep learning, data availability, and computing power, RL have begun to see success in the fields of autonomous vehicles, robotics, and others.
This presentation will focus on the mathematical foundations for two of the most widely used family of RL algorithms, Q-learning and policy gradients, and talk about advancements in the field that lead to the state of the art algorithms widely used today. Additionally, we will talk about considerations on how to apply RL to a problem. Lastly, we will discuss the limitations of RL, as well as how someone can get started today working on RL application and research.
————————————————————————————————————
Event Schedule:
6:30 to 7:00 pm – Mingling
7:00 to 8:00 pm – Introduction to RL by Max Tian (GoldSpot)
8:00 to 8:30 pm – Q&A, Networking
————————————————————————————————————
Speaker Bio:
Max Tian is a Data Scientist working at GoldSpot Discoveries Corp. specializing in using machine learning driven approaches for resource investing. Max holds a MSc in Statistics from McMaster University, as well as a BMath from University of Waterloo and BBA from Wilfrid Laurier University.
————————————————————————————————————
About GoldSpot (TSX-V: SPOT):
GoldSpot Discoveries Corp. is a technology company that takes a novel approach to geoscience by applying artificial intelligence to reduce capital risk and improve success rates in both mineral exploration as well as resource investing. Along with reinforcement learning, GoldSpot has continuously researched on various machine learning and deep learning methods and its applications with respect to geology and investing.
https://goldspot.ca/
