There are 5 repositories under deepracer topic.
A set of Jupyter notebooks to analyze the performance of a DeepRacer model.
AWS DeepRacer Free Student Workshop: Run faster by using your custom waypoints. Step by Step to learn reinforcement learning,
Use AWS RoboMaker and demonstrate running a simulation which trains a reinforcement learning (RL) model to drive a car around a track
Extract from AWS DeepRacer Robomaker Bundle
Udacity AWS ML Foundations Scholarship Course Walkthrough
Interactive detailed analysis tool for AWS DeepRacer logs
This framework makes it easier to create and maintain reward functions for AWS DeepRacer, so you spend more time on machine learning rather than writing lots of Python code! It provides geometry functions and numerous observations not available in DeepRacer itself, such as the ACTUAL SPEED of the car.
A hands on reinforcement machine learning bootcamp, created for Summer of Tech NZ. Designed to be run over a two hour session.
Worksheet and Utilities for AWS DeepRacer – one of the most exciting ways of building strong skills in reinforcement learning and through a hands-on approach. This repository offers: 1) Functionally-rich and flexible reward function 2) Utilities with Jupiter notes for Racing Line calculation and visualisation of track 3) Scripts to parse RoboMaker training and evaluation logs to CSV file 4) Sample Excel file for car behaviour analysis as well as designing and planning new reward curves 5) Coordinates and AWS DeepRacer tracks and images.
Private fork of DeepRacer-for-Cloud; master has been moved upstream.
Some of my reward functions and analysis that helped me throughout my learning
The AWS DeepRacer Event Manager (DREM) is used to run and manage all aspects of in-person events for AWS DeepRacer, an autonomous 1/18th scale race car designed to test reinforcement learning (RL) models by racing on a physical track.
Some tools for AWS Deepracer
Steps to setup and train a DeepRacer model on Mac OSX using CPU
AWS Maching Learning Foundations Scholarship
The fastest way to get rolling with machine learning on AWS. Workshop completed at re:Invent 2018 :blue_car: :red_car:
Code for the AWS DeepRacer Scholarship Challenge - AWS and Udacity are teaming up to teach machine learning and prepare students to test their skills by participating in the world’s first autonomous racing league—the AWS DeepRacer League. Students with the top lap times will earn full scholarships to the Machine Learning Engineer Nanodegree program.
DeepRacer Vision Timer provides a vision-based AI automatic timing system and timer for offline competitions using AWS DeepRacer.
Control the AWS Deepracer directly with a Logitech F710 gamepad
AWS Deepracer organised by ANZ Melbourne collaborated with Amazon to have a run
A port of the DeepRacer software stack for the Raspberry Pi 4.
Reward function experiments for AWS DeepRacer.
Deep Racer in Howard University. Uses a reward function that prioritized staying on the track and following the correct direction. Hyperparameters including batch size, discount factor, and loss type were optimized to achieve a first-place finish. The project combined reinforcement learning and robotics through the DeepRacer platform
A repository for custom tracks for DeepRacer
A simple AWS DeepRacer simulator using Unity with OpenAI gym interface.
Lib for enabling DeepRacer for Cloud (DRfC) functionalities via Python. A wrapper for DRfC
This repository contains practical recommendations and models to improve the performance of your AWS DeepRacer on physical racetracks.
Guides about AWS DeepRacer study group at the Federal University of Ceara (UFC)
This python package rewrite to support the new version Deepracer Console Software version 2.0.383.0
A script that enters a race for you every 5 minutes for AWS DeepRacer