https://github.com/benbaarber/rl

A rust reinforcement learning library
https://github.com/benbaarber/rl

burn deep-learning machine-learning ml reinforcement-learning rl rust

Last synced: 6 months ago
JSON representation

A rust reinforcement learning library

• Host: GitHub
• URL: https://github.com/benbaarber/rl
• Owner: benbaarber
• License: mit
• Created: 2024-04-20T00:34:57.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-08-03T20:43:36.000Z (almost 2 years ago)
• Last Synced: 2025-10-02T06:14:06.658Z (9 months ago)
• Topics: burn, deep-learning, machine-learning, ml, reinforcement-learning, rl, rust
• Language: Rust
• Homepage: https://crates.io/crates/rl
• Size: 442 KB
• Stars: 43
• Watchers: 3
• Forks: 7
• Open Issues: 16
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# rl - A rust reinforcement learning library

[![Current Crates.io Version](https://img.shields.io/crates/v/rl.svg)](https://crates.io/crates/rl)

[![Documentation](https://img.shields.io/badge/Docs-latest-blue)](https://docs.rs/rl/0.4.0/rl/)

[![Rust Version](https://img.shields.io/badge/Rust-v1.79.0+-tan)](https://releases.rs/docs/1.79.0)

*NOTE: I am currently busy with other tasks, so this project is on hiatus. Development will resume soon.*

## About

**rl** is a fully Rust-native reinforcement learning library with the goal of providing a unified RL development experience, aiming to do for RL what libraries like PyTorch did for deep learning. By leveraging Rust's powerful type system and the [**burn**](https://github.com/tracel-ai/burn) library, **rl** enables users to reuse production-ready SoTA algorithms with arbitrary environments, state spaces, and action spaces. 

This project also aims to provide a clean platform for experimentation with new RL algorithms. By combining **burn**'s powerful deep learning features with **rl**'s provided RL sub-algorithms and components, users can create, test, and benchmark their own new experimental agents without having to start from scratch.

Currently, **rl** is in its early stages. Contributors are more than welcome!

## Features

 - High-performance production-ready implementations of all SoTA RL algorithms

 - Detailed logging and training visualization TUI (see image below)

 - Maximum extensibility for creating and testing new experimental algorithms

 - Gym environments

 - A comfortable learning experience for those new to RL

 - General RL peripherals and utility functions

![TUI example](https://github.com/benbaarber/rl/assets/6320364/d0c545bb-a5f4-4487-8e33-1a02a3fb4577)