# FinRL

FinRL®:  Financial Reinforcement Learning. 🔥

Repository: https://github.com/AI4Finance-Foundation/FinRL
Canonical: https://ross.abutalabs.com/products/finrl
Homepage: https://ai4finance.org
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: deep-reinforcement-learning, drl-trading-agents, stock-trading, drl-algorithms, pythorch, tensorflow2, drl-framework, multi-agent-learning, finance, stock-markets, trading-tasks, openai-gym, fintech, algorithmic-trading
Last push: 2026-07-13T23:02:18+00:00
Link (homepage): https://ai4finance.org
Link (site_page): https://ai4finance.org/about

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 43, longevity 100
- inputs: {"age_days": 2229, "days_push": 51, "days_rel": 166, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16108, forks 3478 (observed 2026-08-28T04:11:14.799079+00:00)

## What it is
FinRL is the first open-source deep reinforcement learning framework for financial markets, providing end-to-end pipelines to build, train, and backtest trading agents. It includes Gym-style market environments (FinRL-Meta) and tutorials, with a newer production-oriented FinRL-X stack for live trading.

## Use cases
- train deep RL agents to trade stocks
- backtest algorithmic trading strategies
- build gym-style financial market environments
- research multi-agent reinforcement learning for finance
- benchmark DRL algorithms on trading tasks
- learn quantitative finance with reinforcement learning

## When to choose
- you want an open-source RL framework tailored to financial trading
- you need reproducible market environments and benchmarks for DRL research
- you are prototyping or teaching deep RL trading strategies in Python

## When to avoid
- you need a production live-trading system without additional hardening
- you want a non-Python stack
- you need guaranteed profitable trading rather than a research tool

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, reinforcement-learning, simulation, trading, data-science
- domain: fintech, machine-learning, reinforcement-learning, data-science
- platform: python, cross-platform
- tags: deep-reinforcement-learning, quantitative-trading, trading-agents, backtesting, openai-gym, finance, fintech, stock-trading, pytorch, tensorflow, algorithmic-trading

## Member repositories
- AI4Finance-Foundation/FinRL (main) score 76
- AI4Finance-Foundation/FinRL-Meta (backend) score 64
- AI4Finance-Foundation/FinRL-Tutorials (examples) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:14.799079+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:05:14.401998+00:00, confidence not recorded.
  - readme: https://github.com/AI4Finance-Foundation/FinRL (fetched 2026-08-28T04:11:14.799079+00:00, sha 67adb5b3a9a5)
  - homepage: https://ai4finance.org (fetched 2026-08-29T08:03:00.557613+00:00, sha d3d3e0581dfb)
  - site_page: https://ai4finance.org/about (fetched 2026-08-29T08:03:00.560174+00:00, sha 38823c8faa4a)
  - registry_pypi: https://pypi.org/pypi/finrl/json (fetched 2026-08-29T08:03:00.561851+00:00, sha e7d3eeed9ae6)
  - registry_pypi: https://pypi.org/pypi/finrl-meta/json (fetched 2026-08-29T08:03:00.563367+00:00, sha 3de4feb5c5bc)
- Data as of 2026-08-30T08:39:29.467469+00:00.