https://github.com/janhuenermann/neurojs

A JavaScript deep learning and reinforcement learning library.
https://github.com/janhuenermann/neurojs

deep-learning javascript machine-learning neural-network reinforcement-learning self-driving-car

Last synced: 4 days ago
JSON representation

A JavaScript deep learning and reinforcement learning library.

• Host: GitHub
• URL: https://github.com/janhuenermann/neurojs
• Owner: janhuenermann
• License: mit
• Created: 2016-09-18T23:33:53.000Z (over 8 years ago)
• Default Branch: experimental
• Last Pushed: 2023-10-10T12:55:04.000Z (over 1 year ago)
• Last Synced: 2025-01-03T01:05:35.238Z (11 days ago)
• Topics: deep-learning, javascript, machine-learning, neural-network, reinforcement-learning, self-driving-car
• Language: JavaScript
• Homepage: http://janhuenermann.com/projects/learning-to-drive
• Size: 18.6 MB
• Stars: 4,399
• Watchers: 159
• Forks: 366
• Open Issues: 6
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-deep-reinforcement-learning - https://github.com/janhuenermann/neurojs - commit/janhuenermann/neurojs?label=last%20update) (Neural Networks (NN) and Deep Neural Networks (DNN) / NN/DNN Software Frameworks)
• awesome-github-star - neurojs

README

        


# neurojs

neurojs is a JavaScript framework for deep learning in the browser. It mainly focuses on reinforcement learning, but can be used for any neural network based task. It contains neat demos to visualise these capabilities, for instance a 2D self-driving car. 

Feel free to contribute. The development on such projects is more awesome in a community!

**Note: this repo is no longer maintained since more general frameworks such as TensorFlow-JS emerged, which I recommend you to use.**

### Features

- Implements a full-stack neural-network based machine learning framework

- Extended reinforcement-learning support

	+ Uniform and prioritised replay buffers

	+ Advantage-learning (increasing the action-gap) https://arxiv.org/pdf/1512.04860v1.pdf

	+ Support for **deep-q-networks** and **actor-critic** models (via deep-deterministic-policy-gradients)

- Binary import and export of network configurations (weights etc.)

- High-performance

### Examples

- [Self-driving car](/examples/cars)

- [Advanced XOR](/examples/adv-xor)

- [Andrej Karpathy's Waterworld](/examples/waterworld) (ConvNetJS replaced with NeuroJS)

### Running the examples

```bash

npm install

npm start

```

Open `http://localhost:8080/examples/` in your browser and select the demo you want to run.

### What's next?

- More examples (pong, pendulum, snake,improved cars, etc.)

- Support for web workers

- LSTM and backpropagation through time