AWS DeepRacer Course

Overview

This course will prepare you to create, train, and fine-tune reinforcement learning models in the AWS DeepRacer 3D racing simulator. You will be able to utilize the car's tech specs, assembly, and calibration to train and deploy your racing model using AWS in both simulated and real-world tracks.

Syllabus

Welcome!

Learn the fundamentals of machine learning and reinforcement learning in a fun and engaging way through autonomous driving with AWS DeepRacer.

Get Started with AWS DeepRacer

Receive an overview of what you’ll be learning and doing in the course, learn about the items that come in the AWS DeepRacer box, and assemble and calibrate your vehicle!

Test Drive DeepRacer

First, learn how to navigate the standard AWS DeepRacer online platform. Then, build, train and evaluate your own basic racer in the online simulator!

Reinforcement Learning

Study the basics of reinforcement learning, including agents, actions, environments, states, and rewards. Then, find out how RL is used with AWS DeepRacer, and investigate other applications of RL.

Tuning Your Model

Go more in depth with how parameters, hyperparameters and different reward functions can affect the racer’s performance. Then, enhance your racer by trying out your new skills on your own model!

DeepRacer in the Real World

Deploy your trained model onto your hardware. Next, learn about ROS. Study the differences between simulated and real-world tracks, and then dive even further in-depth on customizing your training.