Course Abstract

Reinforcement Learning recently progressed greatly in the industry as one of the best techniques for sequential decision making and control policies. DeepMind used RL to greatly reduce energy consumption in Google's data center. It has been used to do text summarization, autonomous driving, dialog systems, media advertisements and in finance by JPMorgan Chase. We are at the very beginning of the adoption of these algorithms as systems are required to operate more and more autonomously. In this workshop we will explore Reinforcement Learning, starting from its fundamentals and ending creating our own algorithms. We will use OpenAI gym to try our RL algorithms. OpenAI is a non-profit organization that is committed to open source all their research on Artificial Intelligence. To foster innovation OpenAI created a virtual environment, OpenAi gym, where it's easy to test Reinforcement Learning algorithms.


Learning Objectives

  • The difference between different Reinforcement Learning methods

  • The advantages and disadvantages of each model and how they can be successfully applied in different scenarios

  • The theory behind RL algorithms

  • Understand where it’s possible to use RL algorithms

  • Write RL models in python

Instructor Bio:

Leonardo De Marchi

Head of Data Science and Analytics | Badoo

Leonardo De Marchi

Leonardo De Marchi holds a Master in Artificial intelligence and has worked as a Data Scientist in the sport world, with clients such as the New York Knicks and Manchester United, and with large social networks, like Justgiving. He now works as a Head of Data Scientist and Analytics in Badoo, the largest dating site with over 450 million users. He is also the lead instructor at, a company specialized in Reinforcement Learning, Deep Learning and Machine Learning training. He is also a contractor for several companies and for the European Commission, as an expert in AI and Machine Learning. As an author he wrote “Hands-On Deep Learning” and he authored an online training course for O’Reilly, Introduction to Reinforcement Learning. In the academic world, he also helped set-up the Ph.D. center on Interactive Artificial Intelligence and will take part in the Inner Assessment Board to assign funding to Irish research in AI.

Course Outline

1. Introduction 

  • Who am I, who are you
  • Introduction to different types of learning
  • Deep Learning Basics

2. Bandit methods

  • Bandit Methods concepts 
  • Epsilon greedy
  • Thompson sampling
  • Exercise: Solve a problem using a bandit algorithm 

3. Monte Carlo and tree search 

  • Monte Carlo theory 
  • Monte Carlo Tree search, algorithm explained
  • Exercise: how to use MTC to solve the Frozen Lake problem


  • Introducing DT methods 
  • SARSA explained
  • Visualizing the SARSA algorithm
  • Exercise: Solving a problem using the SARSA algorithm

5. Q-learning

  • Q-learning Explained
  • Visualizing the Q-learning algorithm
  • Exercise: Solving a problem using the Q-learning algorithm

6. Deep Reinforcement Learning 

  • How Deep Learning can be used to approximate functions
  • Theory behind DRL
  • Introduction to Deep Q-network
  • Introduction to Actor Critic Model

Background knowledge

  • The course requires some basic Python knowledge

Use-cases this course could be useful for

  • You’re someone who is passionate about Artificial Intelligence and innovation

  • You work with Machine Learning algorithms and wants to progress your career with innovative techniques

  • You want to become a Machine Learning innovator, anticipating the trends and taking advantage of the new