Stable-Baselines3 (SB3) Tutorial: Getting Started With Reinforcement Learning

Abstract

This tutorial will present the basics of the Gymnasium and Stable-Baselines3 (SB3) libraries in order to apply reinforcement learning in practice.

The session will cover the basics of how to create a custom task and solve it using algorithms from the SB3 library. You will learn how to create a RL model, train it and evaluate it. Because all algorithms share the same interface, we will see how simple it is to switch from one algorithm to another. You will also learn how to define a gym wrapper to customise the training.