/FinRL

FinRL: Financial Reinforcement Learning. 🔥

Primary LanguageJupyter NotebookMIT LicenseMIT

FinRL: Financial Reinforcement Learning twitter facebook google+ linkedin

                               Downloads Downloads Python 3.6 PyPI Documentation Status License

Financial Reinforcement Learning (FinRL) (website) is the first open-source framework to exploit the great potential of deep reinforcement learning. FinRL has evolved into an ecosystem, including hundreds of financial markets, state-of-the-art algorithms, financial applications (portfolio allocation, cryptocurrency trading, high-frequency trading), cloud deployment, etc.

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 pipeline
2.0 (Professional) profession experts ElegantRL algorithms
3.0 (Production) service hedge funds Podracer cloud-native deployment

Outline

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.

Run Stock_NeurIPS2018.ipynb for a quick start.

A video FinRL at the 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
│   	├── 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
│
├── tutorials (educational notebook files)
├── 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
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
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

Status Update

Version History [click to expand]
  • 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

Contributions

  • FinRL is the first open-source framework to demonstrate the great potential of financial reinforcement learning. It has evolved into an ecosystem.
  • The application layer provides interfaces for users to customize FinRL to their own trading tasks. Automated backtesting tool and performance metrics are provided to help quantitative traders iterate trading strategies at a high turnover rate. Profitable trading strategies are reproducible and hands-on tutorials are provided in a beginner-friendly fashion. Adjusting the trained models to the rapidly changing markets is also possible.
  • The agent layer provides state-of-the-art DRL algorithms that are adapted to finance with fine-tuned hyperparameters. Users can add new DRL algorithms.
  • The environment layer includes not only a collection of historical data APIs, but also live trading APIs. They are reconfigured into standard OpenAI gym-style environments. Moreover, it incorporates market frictions and allows users to customize the trading time granularity.

Tutorials

A complete list at blogs

Publications

Title Conference Link Citations Year
FinRL-Meta: FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning NeurIPS 2022 paper code 1 2022
FinRL: Deep reinforcement learning framework to automate trading in quantitative finance ACM International Conference on AI in Finance (ICAIF) paper 19 2021
FinRL-Podracer: High performance and scalable deep reinforcement learning for quantitative finance ACM International Conference on AI in Finance (ICAIF) paper code 8 2021
Explainable deep reinforcement learning for portfolio management: An empirical approach ACM International Conference on AI in Finance (ICAIF) paper code 3 2021
FinRL: A deep reinforcement learning library for automated stock trading in quantitative finance NeurIPS 2020 Deep RL Workshop paper 46 2020
Deep reinforcement learning for automated stock trading: An ensemble strategy ACM International Conference on AI in Finance (ICAIF) paper code 84 2020
Practical deep reinforcement learning approach for stock trading NeurIPS 2018 Workshop on Challenges and Opportunities for AI in Financial Services paper code 113 2018

News

Citing FinRL

@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 FinTech papers. Please check Google Scholar. Closely related papers are given in the list.

Join and Contribute

Welcome to AI4Finance community!

Discuss FinRL via AI4Finance mailing list and AI4Finance Slack channel:

 Follow us on WeChat:

Please check Contributing Guidances.

Contributors

Thank you!

Sponsorship

Welcome gift money to support AI4Finance, a non-profit community.

Network: USDT-TRC20

LICENSE

MIT License

Disclaimer: 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.