https://embed.notionlytics.com/wt/ZXlKd1lXZGxTV1FpT2lKbVlUSXhabVUyTTJSak5XSTBPVGhqWVdNNFkyVm1OV1F5TkRJME1tTXlaQ0lzSW5kdmNtdHpjR0ZqWlZSeVlXTnJaWEpKWkNJNklsRjBaRGt4TVRWNGJVVk9aVlJaYm5BMWIxUkhJbjA9

(estimated time to complete: 30-45 mins)

Welcome to the first tutorial and exercise set for the Delta Academy Intro to Reinforcement Learning!

(Note: Parts of this tutorial have been adapted from Reinforcement Learning: an Introduction)

Admin: Before we start

The code for these tutorials will be hosted on platform called Replit.

Join Replit here

You’ll need to follow this invite look to get access 👇https://replit.com/teams/join/qlyawcwicwtvyxcjotvvvhrytubbssmp-delta-academy-RL2

👆

Replit is great because it means you don’t have to do any installs yourself - the environment is taken care of. However, if you have any trouble here, please contact us on the Slack

(If you haven’t joined Slack, you can join here: https://join.slack.com/t/deltaacademyrl2/shared_invite/zt-1c9kfgn9u-EW58iruk1cDCbepQUsBwUg)

Introduction

The idea that we learn by interacting with our environment probably occurs to us first when we think about learning something. When an infant plays or waves its arms, it has no teacher. However, it interacts with its environment by using its senses (e.g. vision, hearing) and taking actions (e.g. moving, speaking). This connection produces a wealth of information about cause and effect, the consequences of actions, and what to do in order to achieve goals.

1. What is Reinforcement Learning?

The term Reinforcement Learning refers to both a class of problems & a set of solutions.