https://github.com/digitsensitive/neuroevolution-typescript

Neuroevolution library in Typescript
https://github.com/digitsensitive/neuroevolution-typescript

Last synced: 3 months ago
JSON representation

Neuroevolution library in Typescript

• Host: GitHub
• URL: https://github.com/digitsensitive/neuroevolution-typescript
• Owner: digitsensitive
• License: mit
• Created: 2017-08-13T14:51:14.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2023-01-20T12:40:19.000Z (over 2 years ago)
• Last Synced: 2025-03-17T10:52:06.579Z (3 months ago)
• Language: TypeScript
• Homepage:
• Size: 30.3 KB
• Stars: 3
• Watchers: 2
• Forks: 5
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Neuroevolution in Typescript

  

[![GitHub issues](https://img.shields.io/github/issues/digitsensitive/neuroevolution-typescript.svg)](https://github.com/digitsensitive/neuroevolution-typescript/issues)

[![GitHub stars](https://img.shields.io/github/stars/digitsensitive/neuroevolution-typescript.svg)](https://github.com/digitsensitive/neuroevolution-typescript/stargazers)

![Contributions welcome](https://img.shields.io/badge/contributions-welcome-orange.svg)

[![Code style: prettier](https://img.shields.io/badge/code_style-prettier-ff69b4.svg)](https://github.com/prettier/prettier)

[![GitHub license](https://img.shields.io/github/license/digitsensitive/neuroevolution-typescript.svg)](https://github.com/digitsensitive/neuroevolution-typescript)

## Neuroevolution

Neuroevolution, or neuro-evolution, is a form of machine learning that uses evolutionary algorithms to train artificial neural networks. It is most commonly applied in artificial life, computer games, and evolutionary robotics. A main benefit is that neuroevolution can be applied more widely than supervised learning algorithms, which require a syllabus of correct input-output pairs. In contrast, neuroevolution requires only a measure of a network's performance at a task. For example, the outcome of a game (i.e. whether one player won or lost) can be easily measured without providing labeled examples of desired strategies.

## Motivation

This library has been greatly influenced by [xviniette](https://github.com/xviniette/FlappyLearning).

My motivation was to rewrite it in TypeScript.

## Usage

`import * as Neuroevolution from './node_modules/neuroevolution-typescript/main';`

## Ressources

[Deep Neuroevolution: Genetic Algorithms are a Competitive Alternative for

Training Deep Neural Networks for Reinforcement Learning](https://arxiv.org/pdf/1712.06567.pdf)  

## Changelog

[Learn about the latest improvements](https://github.com/digitsensitive/neuroevolution-typescript/blob/master/CHANGELOG.md)

## Contributing

Want to correct a bug, contribute some code, or improve the codes? Excellent! Let me know!

Please read [CONTRIBUTING.md](https://github.com/digitsensitive/neuroevolution-typescript/blob/master/CONTRIBUTING.md) for details on our code of conduct.

## License

This project is licensed under the MIT License - see the [LICENSE.md](https://github.com/digitsensitive/neuroevolution-typescript/blob/master/LICENSE) file for details.