mvrahden/reinforce-js
[INACTIVE] A collection of various machine learning solver. The library is an object-oriented approach (baked with Typescript) and tries to deliver simplified interfaces that make using the algorithms pretty simple.
This is a collection of simple reinforcement learning solvers, providing foundational algorithms like Deep Q-Learning and Temporal Difference Learning. It takes in environment parameters and feedback to train agents that can make decisions. This tool is designed for developers or students looking to learn and experiment with reinforcement learning concepts.
No commits in the last 6 months. Available on npm.
Use this if you are a developer or student wanting to explore and understand how various reinforcement learning algorithms work through a simplified, object-oriented interface.
Not ideal if you need a robust, production-ready library for deploying real-world reinforcement learning applications.
Stars
31
Forks
7
Language
TypeScript
License
MIT
Category
Last pushed
Jun 29, 2018
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mvrahden/reinforce-js"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yoshoku/hnswlib-node
hnswlib-node provides Node.js bindings for Hnswlib
DanRuta/jsNet
Javascript/WebAssembly deep learning library for MLPs and convolutional neural networks
janhuenermann/neurojs
A JavaScript deep learning and reinforcement learning library.
mvrahden/recurrent-js
[INACTIVE] Amazingly simple to build and train various neural networks. The library is an...
DrA1ex/mind-net.js
Fast and simple to use neural network implementation in pure TypeScript with GPU support!