#3939th of 56 in ML frameworks and libraries

finrl

Deep reinforcement learning pipeline for stock and crypto trading research

Stars: 16.6k
License: MIT
Last commit: Oct 2026
Last release: Mar 2026
Language: Jupyter Notebook

Missed the latest GitHub check; these facts may be older.

Overview

FinRL is a Python library for training deep reinforcement learning agents on financial market environments, organized into market environments, DRL agents and applications. It wraps Stable Baselines3, ElegantRL and RLlib agents (A2C, DDPG, PPO, TD3, SAC) behind a train-test-trade pipeline with many data source processors. This repository is the original educational and research version; the maintainers point production use to FinRL-X / FinRL-Trading.

Who it is for: Students and researchers prototyping RL trading strategies

Strengths

Example scripts cover data download, training five DRL agents and backtesting against MVO and DJIA
Data processors for Yahoo Finance, Alpaca, Binance, CCXT, WRDS, Tushare and others
Supports Stable Baselines3, ElegantRL and RLlib agent backends
Backed by several published papers and a Dow 30 tutorial

Weaknesses

README steers new users to FinRL-X; this repo is for education and research
Live trading support is basic, limited to Alpaca
Risk management is limited to Gym environment constraints
README badge lists Python 3.6; supported versions are unclear

What it needs

Docker
Needs Yahoo Finance, Alpaca, Stable Baselines3
Models: A2C, DDPG, PPO, TD3, SAC

Also in ML frameworks and libraries

See all 56

Also in ML frameworks and libraries
Rank	Project	Score
1	transformersPython library defining open models for text, vision, audio and multimodal tasks167.7k starsApache-2.0	95 out of 100
2	pytorchPython tensor library with GPU support and tape-based autograd for deep learning104.7k starscustom license	94 out of 100
3	ultralyticsPython library and CLI for training and running YOLO vision models62.5k starsAGPL-3.0	92 out of 100
#4	supervisionPython toolkit for loading, annotating and counting computer vision detections Live demo ↗ (opens in a new tab)51.2k starsMIT	89 out of 100
#5	pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts37.2k starsApache-2.0	89 out of 100

How to choose

Pick the framework your target models and papers already use.
Check hardware support (CUDA, ROCm, Apple Silicon, TPU) for your machines.
Look at release cadence; a framework that stalls strands your code.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

MIT Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the copyright and license notice in copies you ship.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#39 of 56 in ML frameworks and libraries on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/ai4finance-foundation/finrl.svg)](https://archestack.com/best-of-ai/projects/finrl/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-ai/finrl/" title="finrl on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Open-Source AI on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with finrl filled in.