Skip to main content

AWS DeepRacer

What it is​

A 1/18 scale autonomous racing car, fully programmable, designed to help developers of all skill levels learn and experiment with reinforcement learning (RL).

What it's for​

Provides a fun and practical way to learn RL, allowing users to train models in a simulated environment and then test them on a physical car.

Use cases​

  • Learning and experimentation with reinforcement learning.
  • Autonomous racing competitions to test and optimize RL models.
  • Development of machine learning and artificial intelligence skills.
  • Prototyping of autonomous control and navigation algorithms.

Key points​

  • Reinforcement Learning: Focus on RL, where an agent learns to make decisions through trial and error, receiving rewards for desired actions.
  • Simulation: Allows training models in a virtual environment before deploying them to the physical car.
  • Hardware and Software: Combines a physical car with a cloud software platform for training and evaluation.
  • Community: Has an active community and global competitions to engage users.
  • Accessibility: Designed to be accessible to developers with different levels of ML experience.