Book Image

AI Crash Course

By : Hadelin de Ponteves
5 (4)
Book Image

AI Crash Course

5 (4)
By: Hadelin de Ponteves

Overview of this book

Welcome to the Robot World … and start building intelligent software now! Through his best-selling video courses, Hadelin de Ponteves has taught hundreds of thousands of people to write AI software. Now, for the first time, his hands-on, energetic approach is available as a book. Starting with the basics before easing you into more complicated formulas and notation, AI Crash Course gives you everything you need to build AI systems with reinforcement learning and deep learning. Five full working projects put the ideas into action, showing step-by-step how to build intelligent software using the best and easiest tools for AI programming, including Python, TensorFlow, Keras, and PyTorch. AI Crash Course teaches everyone to build an AI to work in their applications. Once you've read this book, you're only limited by your imagination.
Table of Contents (17 chapters)
16
Index

Building the environment

This time, we have much more to define than just the states, actions, and rewards. Building a self-driving car is a seriously complex problem. Now, I'm not going to ask you to go to your garage and turn yourself into a hybrid AI mechanic; you're simply going to build a virtual self-driving car that moves around a 2D map.

You'll build this 2D map inside a Kivy web app. Kivy is a free and open source Python framework, used for the development of applications like games, or really any kind of mobile app. Check out the website here: https://kivy.org/#home.

The whole environment for this project is built with Kivy, from start to finish. The development of the map and the virtual car has nothing to do with AI, so we won't go line by line through the code that implements it.

However, I am going to describe the features of the map. For those of you curious to know about exactly how the map is built, I've provided a fully...