FinRL: Financial Reinforcement Learning

                              

FinGPT: Open-source for open-finance! Revolutionize FinTech.

Check out our latest competition: ACM ICAIF 2023 FinRL Contest

Financial reinforcement learning (FinRL) (Document website) is the first open-source framework for financial reinforcement learning. FinRL has evolved into an ecosystem

Dev Roadmap	Stage	Users	Project	Desription
0.0 (Preparation)	entrance	practitioners	FinRL-Meta	gym-style market environments
1.0 (Proof-of-Concept)	full-stack	developers	this repo	automatic pipeline
2.0 (Professional)	profession	experts	ElegantRL	algorithms
3.0 (Production)	service	hedge funds	Podracer	cloud-native deployment

Outline

• Overview
• File Structure
• Supported Data Sources
• Installation
• Status Update
• Tutorials
• Publications
• News
• Citing FinRL
• Join and Contribute
  • Contributors
  • Sponsorship
• LICENSE

Overview

FinRL has three layers: market environments, agents, and applications. For a trading task (on the top), an agent (in the middle) interacts with a market environment (at the bottom), making sequential decisions.

A quick start: Stock_NeurIPS2018.ipynb. Videos FinRL at AI4Finance Youtube Channel.

File Structure

The main folder finrl has three subfolders applications, agents, meta. We employ a train-test-trade pipeline with three files: train.py, test.py, and trade.py.

FinRL
├── finrl (main folder)
│   ├── applications
│   	├── Stock_NeurIPS2018
│   	├── imitation_learning
│   	├── cryptocurrency_trading
│   	├── high_frequency_trading
│   	├── portfolio_allocation
│   	└── stock_trading
│   ├── agents
│   	├── elegantrl
│   	├── rllib
│   	└── stablebaseline3
│   ├── meta
│   	├── data_processors
│   	├── env_cryptocurrency_trading
│   	├── env_portfolio_allocation
│   	├── env_stock_trading
│   	├── preprocessor
│   	├── data_processor.py
│       ├── meta_config_tickers.py
│   	└── meta_config.py
│   ├── config.py
│   ├── config_tickers.py
│   ├── main.py
│   ├── plot.py
│   ├── train.py
│   ├── test.py
│   └── trade.py
│
├── examples
├── unit_tests (unit tests to verify codes on env & data)
│   ├── environments
│   	└── test_env_cashpenalty.py
│   └── downloaders
│   	├── test_yahoodownload.py
│   	└── test_alpaca_downloader.py
├── setup.py
├── requirements.txt
└── README.md

Supported Data Sources

Data Source	Type	Range and Frequency	Request Limits	Raw Data	Preprocessed Data
Akshare	CN Securities	2015-now, 1day	Account-specific	OHLCV	Prices&Indicators
Alpaca	US Stocks, ETFs	2015-now, 1min	Account-specific	OHLCV	Prices&Indicators
Baostock	CN Securities	1990-12-19-now, 5min	Account-specific	OHLCV	Prices&Indicators
Binance	Cryptocurrency	API-specific, 1s, 1min	API-specific	Tick-level daily aggegrated trades, OHLCV	Prices&Indicators
CCXT	Cryptocurrency	API-specific, 1min	API-specific	OHLCV	Prices&Indicators
EODhistoricaldata	US Securities	Frequency-specific, 1min	API-specific	OHLCV	Prices&Indicators
IEXCloud	NMS US securities	1970-now, 1 day	100 per second per IP	OHLCV	Prices&Indicators
JoinQuant	CN Securities	2005-now, 1min	3 requests each time	OHLCV	Prices&Indicators
QuantConnect	US Securities	1998-now, 1s	NA	OHLCV	Prices&Indicators
RiceQuant	CN Securities	2005-now, 1ms	Account-specific	OHLCV	Prices&Indicators
Tushare	CN Securities, A share	-now, 1 min	Account-specific	OHLCV	Prices&Indicators
WRDS	US Securities	2003-now, 1ms	5 requests each time	Intraday Trades	Prices&Indicators
YahooFinance	US Securities	Frequency-specific, 1min	2,000/hour	OHLCV	Prices&Indicators

OHLCV: open, high, low, and close prices; volume. adjusted_close: adjusted close price

Technical indicators: 'macd', 'boll_ub', 'boll_lb', 'rsi_30', 'dx_30', 'close_30_sma', 'close_60_sma'. Users also can add new features.

Installation

• Install description for all operating systems (MAC OS, Ubuntu, Windows 10)
• FinRL for Quantitative Finance: Install and Setup Tutorial for Beginners

Status Update

Version History [click to expand]

• 2022-06-25 0.3.5: Formal release of FinRL, neo_finrl is chenged to FinRL-Meta with related files in directory: meta.
• 2021-08-25 0.3.1: pytorch version with a three-layer architecture, apps (financial tasks), drl_agents (drl algorithms), neo_finrl (gym env)
• 2020-12-14 Upgraded to Pytorch with stable-baselines3; Remove tensorflow 1.0 at this moment, under development to support tensorflow 2.0
• 2020-11-27 0.1: Beta version with tensorflow 1.5

Tutorials

• [Towardsdatascience] Deep Reinforcement Learning for Automated Stock Trading

A complete list at blogs

Publications

Title	Conference/Journal	Link	Citations	Year
Dynamic Datasets and Market Environments for Financial Reinforcement Learning	Machine Learning - Nature	paper code	1	2024
FinRL-Meta: FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning	NeurIPS 2022	paper code	12	2022
FinRL: Deep reinforcement learning framework to automate trading in quantitative finance	ACM International Conference on AI in Finance (ICAIF)	paper	49	2021
FinRL: A deep reinforcement learning library for automated stock trading in quantitative finance	NeurIPS 2020 Deep RL Workshop	paper	87	2020
Deep reinforcement learning for automated stock trading: An ensemble strategy	ACM International Conference on AI in Finance (ICAIF)	paper code	154	2020
Practical deep reinforcement learning approach for stock trading	NeurIPS 2018 Workshop on Challenges and Opportunities for AI in Financial Services	paper code	164	2018

News

• [央广网] 2021 IDEA大会于福田圆满落幕：群英荟萃论道AI 多项目发布亮点纷呈
• [央广网] 2021 IDEA大会开启AI思想盛宴 沈向洋理事长发布六大前沿产品
• [IDEA新闻] 2021 IDEA大会发布产品FinRL-Meta——基于数据驱动的强化学习金融风险模拟系统
• [知乎] FinRL-Meta基于数据驱动的强化学习金融元宇宙
• [量化投资与机器学习] 基于深度强化学习的股票交易策略框架（代码+文档)
• [运筹OR帷幄] 领读计划NO.10 | 基于深度增强学习的量化交易机器人：从AlphaGo到FinRL的演变过程
• [深度强化实验室] 【重磅推荐】哥大开源“FinRL”: 一个用于量化金融自动交易的深度强化学习库
• [商业新知] 金融科技讲座回顾|AI4Finance: 从AlphaGo到FinRL
• [Kaggle] Jane Street Market Prediction
• [矩池云Matpool] 在矩池云上如何运行FinRL股票交易策略框架
• [财智无界] 金融学会常务理事陈学彬: 深度强化学习在金融资产管理中的应用
• [Neurohive] FinRL: глубокое обучение с подкреплением для трейдинга
• [ICHI.PRO] 양적 금융을위한 FinRL: 단일 주식 거래를위한 튜토리얼
• [知乎] 基于深度强化学习的金融交易策略（FinRL+Stable baselines3，以道琼斯30股票为例）
• [知乎] 动态数据驱动的金融强化学习
• [知乎] FinRL的W&B化+超参数搜索和模型优化(基于Stable Baselines 3）

Citing FinRL

@article{dynamic_datasets,
    author = {Liu, Xiao-Yang and Xia, Ziyi and Yang, Hongyang and Gao, Jiechao and Zha, Daochen and Zhu, Ming and Wang, Christina Dan and Wang, Zhaoran and Guo, Jian},
    title = {Dynamic Datasets and Market Environments for Financial Reinforcement Learning},
    journal = {Machine Learning - Springer Nature},
    year = {2024}
}

@article{liu2022finrl_meta,
  title={FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning},
  author={Liu, Xiao-Yang and Xia, Ziyi and Rui, Jingyang and Gao, Jiechao and Yang, Hongyang and Zhu, Ming and Wang, Christina Dan and Wang, Zhaoran and Guo, Jian},
  journal={NeurIPS},
  year={2022}
}

@article{liu2021finrl,
    author  = {Liu, Xiao-Yang and Yang, Hongyang and Gao, Jiechao and Wang, Christina Dan},
    title   = {{FinRL}: Deep reinforcement learning framework to automate trading in quantitative finance},
    journal = {ACM International Conference on AI in Finance (ICAIF)},
    year    = {2021}
}

@article{finrl2020,
    author  = {Liu, Xiao-Yang and Yang, Hongyang and Chen, Qian and Zhang, Runjia and Yang, Liuqing and Xiao, Bowen and Wang, Christina Dan},
    title   = {{FinRL}: A deep reinforcement learning library for automated stock trading in quantitative finance},
    journal = {Deep RL Workshop, NeurIPS 2020},
    year    = {2020}
}

@article{liu2018practical,
  title={Practical deep reinforcement learning approach for stock trading},
  author={Liu, Xiao-Yang and Xiong, Zhuoran and Zhong, Shan and Yang, Hongyang and Walid, Anwar},
  journal={NeurIPS Workshop on Deep Reinforcement Learning},
  year={2018}
}

We published FinRL papers that are listed at Google Scholar. Previous papers are given in the list.

Join and Contribute

Welcome to AI4Finance community!

Please check Contributing Guidances.

Contributors

Thank you!

LICENSE

MIT License

Disclaimer: We are sharing codes for academic purpose under the MIT education license. Nothing herein is financial advice, and NOT a recommendation to trade real money. Please use common sense and always first consult a professional before trading or investing.