Rishit-katiyar / race-test-codes

it my race codes with all the different iterations

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

DeepRace Test Codes 🏎️

Welcome to the DeepRace Test Codes repository! This repository contains optimized and advanced reward functions for training AWS DeepRacer models. Use these codes to enhance the performance of your DeepRacer models and dominate the race track! 🚀

Table of Contents

  1. Introduction
  2. Installation
  3. Usage
  4. Contributing
  5. License

Introduction

AWS DeepRacer is a fully autonomous 1/18th scale race car designed to help developers get started with reinforcement learning. These test codes provide advanced reward functions to optimize the training process of DeepRacer models. By incorporating various parameters such as distance from center, track width, speed, steering angle, and progress, these reward functions aim to improve the racing performance of DeepRacer models.

Installation

To use these advanced reward functions, follow these steps:

  1. Clone this repository to your local machine:
git clone https://github.com/Rishit-katiyar/race-test-codes.git
  1. Navigate to the cloned directory:
cd race-test-codes
  1. Set up your AWS DeepRacer environment and training pipeline according to AWS documentation.

  2. Replace the reward function in your training script with one of the provided reward functions from this repository.

  3. Start training your DeepRacer model with the updated reward function!

Usage

To use these reward functions effectively, consider the following tips:

  • Experiment with different reward functions to find the one that best suits your training objectives.
  • Fine-tune reward parameters such as track width, distance from center, speed thresholds, and steering angle thresholds to optimize performance.
  • Monitor training progress and adjust reward functions accordingly to achieve desired racing behavior.
  • Share your experiences and contribute new reward functions to this repository to help the DeepRacer community grow!

Contributing

Contributions to this repository are welcome! To contribute, follow these steps:

  1. Fork this repository and clone it to your local machine.
  2. Create a new branch for your feature or improvement:
git checkout -b feature-name
  1. Make your changes and commit them with descriptive messages:
git commit -m "Add feature XYZ"
  1. Push your changes to your forked repository:
git push origin feature-name
  1. Open a pull request to the main repository, explaining the purpose and details of your changes.

License

This project is licensed under the GNU General Public License v3.0. See the LICENSE file for details.

About

it my race codes with all the different iterations

License:GNU General Public License v3.0


Languages

Language:Python 100.0%