#181 · Primary category: Deep Learning Frameworks
neurojs
A JavaScript deep learning and reinforcement learning library.
Project last updated:10/10/23
GitHub Stars
4.4K
Forks
362
Contributors
6
License
MIT
Why we included this project
neurojs lets you run reinforcement learning entirely in the browser, and its demos are the best part: a self-driving car, an advanced XOR, and a reimplementation of Karpathy's Waterworld. It's a compact JavaScript library with support for deep-Q-networks, actor-critic models via deep deterministic policy gradients, and both uniform and prioritized replay buffers. The author has stopped maintaining it and recommends TensorFlow.js for production work, so treat this as a learning tool and reference implementation rather than a dependency for new projects.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
tensorflow
An Open Source Machine Learning Framework for Everyone
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
keras
Deep Learning for humans
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.