Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

FinRL®: Financial Reinforcement Learning. 🔥

License

NotificationsYou must be signed in to change notification settings

AI4Finance-Foundation/FinRL

Repository files navigation

image

FinRL®: Financial Reinforcement Learningtwitterfacebookgoogle+linkedin

DownloadsDownloadsJoin DiscordPython 3.6PyPIDocumentation StatusLicense

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

Visitors

Financial reinforcement learning (FinRL®) (Document website) isthe first open-source framework for financial reinforcement learning. FinRL has evolved into anecosystem

  • 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. VideosFinRL atAI4Finance Youtube Channel.

File Structure

The main folderfinrl has three subfoldersapplications, agents, meta. We employ atrain-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]
  • 2022-06-250.3.5: Formal release of FinRL, neo_finrl is chenged to FinRL-Meta with related files in directory:meta.
  • 2021-08-250.3.1: pytorch version with a three-layer architecture, apps (financial tasks), drl_agents (drl algorithms), neo_finrl (gym env)
  • 2020-12-14Upgraded toPytorch with stable-baselines3; Remove tensorflow 1.0 at this moment, under development to support tensorflow 2.0
  • 2020-11-270.1: Beta version with tensorflow 1.5

Tutorials

Publications

TitleConference/JournalLinkCitationsYear
Dynamic Datasets and Market Environments for Financial Reinforcement LearningMachine Learning - Springer Naturepapercode72024
FinRL-Meta: FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement LearningNeurIPS 2022papercode372022
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)papercode1542020
Practical deep reinforcement learning approach for stock tradingNeurIPS 2018 Workshop on Challenges and Opportunities for AI in Financial Servicespapercode1642018

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 publishedFinRL papers that are listed atGoogle Scholar. Previous papers are given in thelist.

Join and Contribute

Welcome toAI4Finance community!

Please checkContributing Guidances.

Contributors

Thank you!

LICENSE

MIT License

Trademark DisclaimerFinRL® is a registered trademark.This license does not grant permission to use the FinRL name, logo, or related trademarkswithout 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.


[8]ページ先頭

©2009-2025 Movatter.jp