Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
AI4Finance-Foundation
GitHub Repository: AI4Finance-Foundation/FinRL
 Path: blob/master/README.md
726 views
image

FinRL®: Financial Reinforcement Learning twitter facebook google+ linkedin

Downloads Downloads Python 3.6 PyPI Documentation Status License

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

Visitors

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

  • FinRL-DeepSeek: LLM-Infused Risk-Sensitive Reinforcement Learning for Trading Agents

Dev RoadmapStageUsersProjectDescription
0.0 (Preparation)entrancepractitionersFinRL-Metagym-style market environments
1.0 (Proof-of-Concept)full-stackdevelopersthis repoautomatic pipeline
2.0 (Professional)professionexpertsElegantRLalgorithms
3.0 (Production)servicehedge fundsPodracercloud-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.

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 SourceTypeRange and FrequencyRequest LimitsRaw DataPreprocessed Data
AkshareCN Securities2015-now, 1dayAccount-specificOHLCVPrices&Indicators
AlpacaUS Stocks, ETFs2015-now, 1minAccount-specificOHLCVPrices&Indicators
BaostockCN Securities1990-12-19-now, 5minAccount-specificOHLCVPrices&Indicators
BinanceCryptocurrencyAPI-specific, 1s, 1minAPI-specificTick-level daily aggegrated trades, OHLCVPrices&Indicators
CCXTCryptocurrencyAPI-specific, 1minAPI-specificOHLCVPrices&Indicators
EODhistoricaldataUS SecuritiesFrequency-specific, 1minAPI-specificOHLCVPrices&Indicators
IEXCloudNMS US securities1970-now, 1 day100 per second per IPOHLCVPrices&Indicators
JoinQuantCN Securities2005-now, 1min3 requests each timeOHLCVPrices&Indicators
QuantConnectUS Securities1998-now, 1sNAOHLCVPrices&Indicators
RiceQuantCN Securities2005-now, 1msAccount-specificOHLCVPrices&Indicators
SinopacTaiwan securities2023-04-13~now, 1minAccount-specificOHLCVPrices&Indicators
TushareCN Securities, A share-now, 1 minAccount-specificOHLCVPrices&Indicators
WRDSUS Securities2003-now, 1ms5 requests each timeIntraday TradesPrices&Indicators
YahooFinanceUS SecuritiesFrequency-specific, 1min2,000/hourOHLCVPrices&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]

  • 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

Publications

TitleConference/JournalLinkCitationsYear
Dynamic Datasets and Market Environments for Financial Reinforcement LearningMachine Learning - Springer Naturepaper code72024
FinRL-Meta: FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement LearningNeurIPS 2022paper code372022
FinRL: Deep reinforcement learning framework to automate trading in quantitative financeACM International Conference on AI in Finance (ICAIF)paper492021
FinRL: A deep reinforcement learning library for automated stock trading in quantitative financeNeurIPS 2020 Deep RL Workshoppaper872020
Deep reinforcement learning for automated stock trading: An ensemble strategyACM International Conference on AI in Finance (ICAIF)paper code1542020
Practical deep reinforcement learning approach for stock tradingNeurIPS 2018 Workshop on Challenges and Opportunities for AI in Financial Servicespaper code1642018

News

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

Trademark Disclaimer

FinRL® is a registered trademark.
This license does not grant permission to use the FinRL name, logo, or related trademarks
without prior written consent, except as permitted by applicable trademark law.
For trademark inquiries or permissions, please contact: contact@finrl.ai

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.