A Conceptual Introduction to Reinforcement Learning

09:00-12:30, January 25

Workshop / Overview

In this workshop we will introduce the important concepts and methodologies that underpin (deep) Reinforcement Learning, using a single (straightforward) running example (sliding puzzle).

Overview

  • What is RL and how is it different from other AI topics?
  • The RL vocabulary:  states, actions, rewards and policies
  • Value functions and the Bellman equations
  • Solving an RL problem:  Dynamic Programming and Q-learning
  • Scaling up RL: function approximations in deep RL

Workshop / Outcome

Participants will have an intermediate understanding of RL concepts and methodologies that will enable them to access recent literature and apply RL methodologies to similar problems. 

Workshop / Difficulty

Beginner level

Workshop / Prerequisites

  • Python programming
  • Google account (for using Colab)
  • Own laptop with a modern browser

Track / Co-organizers

Bram Vandendriessche

Evolutionary Architect, ToThePoint

Kevin Smeyers

Evolutionary Architect, ToThePoint

Katrien Van Meulder

Evolutionary Architect, ToThePoint

AMLD EPFL 2020 / Workshops

Applied Machine Learning with R

With Dirk Wulff

09:00-17:00 January 25

Augmenting the Web browsing experience using machine learning

With Tudor Avram, Oleksandr Paraska, Vasily Kuznetsov & Levan Tsinadze

09:00-12:30 January 25

Feature Engineering for Spatial Data Analysis

With Caio Miyashiro, Selim Onat & Eva Jaumann

09:00-17:00 January 25

AMLD / Global partners