BeTomorrow/ReImproveJS
A framework using TensorFlow.js for Deep Reinforcement Learning
This is a JavaScript library for building deep reinforcement learning models directly in a web browser. It allows developers to create AI agents that learn through trial and error within a simulated environment. You provide the agent's sensory inputs and define rewards or penalties for its actions, and the library helps it learn optimal strategies. This is used by web developers building interactive simulations, games, or other browser-based applications where AI agents need to adapt and learn.
122 stars. No commits in the last 6 months.
Use this if you are a JavaScript developer who wants to implement AI agents that learn by interacting with an environment directly within a web browser, leveraging the user's GPU.
Not ideal if you need to use convolutional neural networks for your agent's learning, or if you require a library that is actively maintained and updated.
Stars
122
Forks
16
Language
TypeScript
License
MIT
Category
Last pushed
Jun 22, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BeTomorrow/ReImproveJS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OpenMined/syft.js
The official Syft worker for Web and Node, built in Javascript
transcranial/keras-js
Run Keras models in the browser, with GPU support using WebGL
ewfian/faiss-node
Node.js bindings for faiss
nikhilk/node-tensorflow
Node.js + TensorFlow
beenotung/tensorflow-helpers
Helper functions to use tensorflow in nodejs for transfer learning, image classification, and more