Introduction to Deep Reinforcement Learning

Course Description

This course will cover the basics of deep reinforcement learning with a focus on core algorithms. We will look at standard reinforcement learning methods like Q-learning and policy gradients along with their neural/deep counterparts. We will also cover a number of practical implementation issues like reward scaling and how to deal with large or continuous action spaces.

Course tools

  • Python
  • TensorFlow 2

Prerequisites

  • Basic deep learning/neural networks (CNNs, SGD, etc)
  • Basic RL  (MDPs, value functions, TD, etc).

Level of complexity of course

Intermediate

Lecturer

Dr. Volodymyr Mnih

Research Scientist at DeepMind

Volodymyr is a Research Scientist at DeepMind where he works primarily on deep reinforcement learning. Prior to joining DeepMind, Volodymyr received a Ph.D. from the University of Toronto working with Geoffrey Hinton and an MSc from the University of Alberta working with Csaba Szepesvari.

Fields of interests: Reinforcement Learning, Deep Learning

Contacts: [email protected]