Physical Society Colloquium

Deep Reinforcement Learning: From Basics to Applications

Joelle Pineau

School of Computer Science
McGill University

In recent years, significant progress has been made in solving challenging problems across various domains using deep reinforcement learning. In this talk I will review basic models and algorithms for this paradigm and will describe several applications, ranging from healthcare to robotics. I will also discuss challenges that arise in experimental techniques and reporting procedures in deep RL.