A Conceptual Introduction to Reinforcement Learning
Most of our classroom training courses take place in Belgium (Edegem) or The Netherlands (Breda). Please click the button with the desired date to check the exact location of the training.
This workshop introduces participants to the concepts and methodologies of Reinforcement Learning (RL). It will enable them to gain an intermediate understanding of what Reinforcement Learning is and in which settings it could be useful. Moreover, the participants will be able to understand and apply recent literature about this topic, qualifying them to further expand the knowledge obtained during the workshop.
This course is intended for everyone who is interested in Reinforcement Learning and who wants to gain a better understanding of the topic. It aims to introduce the relevant concepts and methodologies underpinning (deep) Reinforcement Learning through a single, straightforward running example.
In this workshop, we will introduce the important concepts and methodologies that underpin (deep) Reinforcement Learning, using a single (straightforward) running example.
No previous machine learning knowledge is required, although we definitely recommend some familiarity with Python programming.
You need a Google Account so you can start using Colab.
This is a BYOD (Bring Your Own Device) training. Please bring your own laptop to the course. Also, make sure to have an up-to-date browser installed.
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 Reinforcement Learning