AI4Finance-Foundation /FinRL
FinRL®: Financial Reinforcement Learning. 🔥
★ 17,087⑂ 3,653👁 231⑃ 581● 786▤ 1
+18
日增长
17,087
stars
3,653
forks
231
watchers
581
prs
786
issues
1
releases
README
FinRL: Financial Reinforcement Learning → FinRL-X
!License
!
!
!
!
[!IMPORTANT]
FinRL-X is the next-generation evolution of FinRL, designed for AI-native, modular, and production-oriented quantitative trading.
- This repository (FinRL) preserves the original end-to-end educational and research framework.
- For the latest architecture, live trading deployment, and production-focused development, please use FinRL-X / FinRL-Trading.
FinRL® is widely recognized as the first open-source framework for financial reinforcement learning.
This repository contains the original FinRL library for education, benchmarking, and research prototyping.
For the next-generation AI-native and production-oriented trading stack, please visit FinRL-X / FinRL-Trading.
FinRL Ecosystem Roadmap
| Generation | Positioning | Target Users | Repository | Description |
|----|----|----|----|----|
| FinRL-Meta | Market Environments | Practitioners | FinRL-Meta | Gym-style financial market environments and benchmarks |
| FinRL | Classic End-to-End Framework | Learners, Developers, Researchers | FinRL | Original train-test-trade pipeline for financial reinforcement learning |
| ElegantRL | Algorithm Layer | Researchers and Experts | ElegantRL | Lightweight and elegant DRL algorithms |
| FinRL-X | Next Generation / Production | Professional traders, institutions, hedge funds | FinRL-Trading | AI-native modular infrastructure for deployment-aware quantitative trading |
Recommended for new users: Start with FinRL-X / FinRL-Trading if you are building modern or production-oriented trading systems.
🔄 FinRL-X vs. FinRL: What Changed
| Capability | FinRL (Stage 1.0) | FinRL-X (Stage 3.0) |
|---|---|---|
| Paradigm | Deep Reinforcement Learning | AI-Native (ML + DRL + LLM-ready) |
| Architecture | Three-layer coupled monolith | Fully decoupled modular layers |
| Strategies | DRL agents (A2C, DDPG, PPO, SAC, TD3) | ML selection + DRL timing + extensible base |
| Data Layer | 14 manually-wired processors | Auto-select: Yahoo Finance → FMP → WRDS |
| Backtesting | Custom hand-rolled evaluation loops | Professional bt library engine |
| Live Trading | Basic Alpaca support | Full multi-account integration + risk controls |
| Configuration | config.py + config_tickers.py | Type-safe Pydantic + .env multi-env |
| Risk Management | Gym environment constraints only | Order · portfolio · strategy-level controls |
| Target Users | Researchers & students | Quants, institutions, production deployments |
| Paper | arXiv:2011.09607 | arXiv:2603.21330 |
FinGPT: an open-source project for financial large language models, designed for research and real-world FinTech applications.
!Visitors
Outline
- Overview
- File Structure
- Supported Data Sources
- Installation
- Status Update
- Tutorials
- Publications
- News
- Citing FinRL
- Join and Contribute
- Contributors
- Sponsorship
- LICENSE
Project Contributors
FinRL® is an open-source financialTop issues
#573Paper Trading Demo does not handle tick level data28 comments · 2022-04-17#915Can't install FinRL19 comments · 2023-03-08#1011Error occurs in PaperTrading_Demo notbook while running on Colab16 comments · 2023-05-17#962Yahoo data downloader does not download any data??16 comments · 2023-04-05#1013Google colab Stock_NeurIPS2018_SB3.ipynb StockTradingEnv.reset() got an unexpected keyword argument 'seed'15 comments · 2023-05-21#445FinRL_PaperTrading_Demo - trading operation quantity is 011 comments · 2022-01-24#1100Problem with Imports10 comments · 2023-09-12#1070Dow Jones outperforming ensemble strategy in FinRL_Ensemble_StockTrading_ICAIF_2020 notebook10 comments · 2023-08-05
Discussions
#1442Same number of price bars, wrong dates: an offline reliability example0 comments · 2026-09-10#1433Open-source PyTorch multi-factor stack with public CSI 300 validation0 comments · 2026-08-06#1432We built 19 Borsa Istanbul research systems but still cannot prove a real trading edge — what are we missing?0 comments · 2026-07-29#1426[Show and tell] BDE Score - Open Source Multi-Factor Stock Analysis (US/HK/A-share)0 comments · 2026-07-11#1425🤖 BDE Score — 开源 AI 多因子评分 API,覆盖 US/HK/A 股,符合 EU AI Act0 comments · 2026-07-10#1419Open source Claude Code skills for options flow analysis — complements FinRL signal generation0 comments · 2026-05-13#1418Claude Code skill for options flow analysis — free, SKILL.md format, real results0 comments · 2026-05-13#1415Proposal: add a weight-based trading environment with composite reward shaping0 comments · 2026-04-13
Latest release
v0.3.8 v0.3.8 2026-03-20Add FinRL Stock Trading 2026 tutorial with 3 scripts: - FinRL_StockTrading_2026_1_data.py: Data download & preprocessing - FinRL_StockTrading_2026_2_train.py: Train 5 DRL agents (A2C, DDPG, PPO, TD3, SAC) - FinRL_StockTrading_2026_3_Backtest.py: Backtest & compare with MVO/DJIA