← 开源
janhuenermann

neurojs

A JavaScript deep learning and reinforcement learning library.

Model DevelopmentDeep Learning FrameworksReinforcement LearningJavaScript
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
4.37k
Star
359
Fork
+2
本周
4
贡献者
创建于 2016-09-18 · 更新于 2026-10-13 · 今日第 7626 名
主要开发者
janhuenermannlunzhanghavefive
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. I appreciate any support, because frankly this is a big project to maintain!

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

Running the examples

npm install
npm start

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

Future

  • More examples (pong, improved cars, etc.)
  • Support for web workers
  • LSTM and backpropagation through time
排名相邻
同类项目