AWS DeepRacer

From AWS DeepRacer Community Wiki
Jump to navigation Jump to search

AWS DeepRacer is a 1/18th scale race car which gives you an interesting and fun way to get started with reinforcement learning (RL). It is a car designed to test RL models by racing on a physical track. Using a camera to view the track and a reinforcement model to control throttle and steering, the car shows how a model trained in a simulated environment can be transferred to the real-world. The combination of console, simulator, and car provides a complete solution to experiment with RL algorithms and generalization methods

With AWS DeepRacer, you now have a way to get hands-on with RL, experiment, and learn through autonomous driving. You can get started with the virtual car and tracks in the cloud-based 3D racing simulator, and for a real-world experience, you can deploy your trained models onto AWS DeepRacer and race your friends, or take part in the global AWS DeepRacer League.

When talking about DeepRacer, usually three elements are mentioned:

  • The AWS DeepRacer Console - AWS service providing an easy way to begin training a model without prior experience in machine learning and without the need to purchase the car
  • The 1/18th scale race car - the physical device for an ultimate evaluation of the model
  • The AWS DeepRacer League - A global competition both in real life and virtual space with the final taking place at the AWS re:Invent conference