AI4Finance-Foundation/FinRL-Meta

FinRL®-Meta: A Metaverse of Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning

Part of the FinRL ecosystem. For the next-generation production-oriented trading stack, see FinRL-X / FinRL-Trading.

FinRL®-Meta is the market environment and benchmark layer of the FinRL ecosystem. It builds a universe of market environments for data-driven financial reinforcement learning and helps users easily develop, evaluate, and compare trading agents across diverse financial tasks.

For the next-generation AI-native modular trading infrastructure and production-oriented deployment workflow, please visit FinRL-X / FinRL-Trading.

FinRL Ecosystem

• FinRL: the original open-source end-to-end framework for financial reinforcement learning
• FinRL-Meta: market environments and benchmarks for data-driven financial reinforcement learning
• ElegantRL: lightweight deep reinforcement learning algorithms
• FinRL-X / FinRL-Trading: next-generation AI-native modular infrastructure for production-oriented quantitative trading

Outline

• News and Tutorials
• Our Goals
• Design Principles
• Overview
• Plug-and-Play
• Training-Testing-Trading
• Our Vision

News and Tutorials

• [MLearning.ai] Financial Metaverse as a Playground for Financial Machine Learning
• [DataDrivenInvestor] FinRL-Meta: A Universe of Near Real-Market En­vironments for Data­-Driven Financial Reinforcement Learning
• [深圳特区报] 深港两城深度融合 用“创新”续写“春天的故事” 香港特别行政区联络办公室
• [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

Our Goals

• To provide benchmarks and facilitate fair comparisons, we allow researchers to evaluate different strategies on the same dataset. Also, it would help researchers to better understand the “black-box” nature (deep neural network-based) of DRL algorithms.
• To reduce the simulation-reality gap: existing works use backtesting on historical data, while the actual performance may be quite different.
• To reduce the data pre-processing burden, so that quants can focus on developing and optimizing strategies.

Design Principles

• Plug-and-Play (PnP): Modularity; Handle different markets (say T0 vs. T+1)
• Completeness and universal: Multiple markets; Various data sources (APIs, Excel, etc); User-friendly variables.
• Layer structure and extensibility: Three layers including: data layer, environment layer, and agent layer. Layers interact through end-to-end interfaces, achieving high extensibility.
• “Training-Testing-Trading” pipeline: simulation for training and connecting real-time APIs for testing/trading, closing the sim-real gap.
• Efficient data sampling: accelerate the data sampling process is the key to DRL training! From the ElegantRL project. we know that multi-processing is powerful to reduce the training time (scheduling between CPU + GPU).
• Transparency: a virtual env that is invisible to the upper layer
• Flexibility and extensibility: Inheritance might be helpful here

Overview

We utilize a layered structure in FinRL-Meta, as shown in the figure above, that consists of three layers: data layer, environment layer, and agent layer. Each layer executes its functions and is independent. Meanwhile, layers interact through end-to-end interfaces to implement the complete workflow of algorithm trading. Moreover, the layer structure allows easy extension of user-defined functions.

FinRL-Meta focuses on the data layer and environment layer for financial reinforcement learning research and benchmarking. For full-stack deployment and production-oriented trading infrastructure, please see FinRL-X / FinRL-Trading.

DataOps

DataOps applies the ideas of lean development and DevOps to the data analytics field. DataOps practices have been developed in companies and organizations to improve the quality and efficiency of data analytics. These implementations consolidate various data sources, unify and automate the pipeline of data analytics, including data accessing, cleaning, analysis, and visualization.

However, the DataOps methodology has not been applied to financial reinforcement learning researches. Most researchers access data, clean data, and extract technical indicators (features) in a case-by-case manner, which involves heavy manual work and may not guarantee the data quality.

To deal with financial big data (unstructured), we follow the DataOps paradigm and implement an automatic pipeline in the following figure: task planning, data processing, training-testing-trading, and monitoring agents’ performance. Through this pipeline, we continuously produce DRL benchmarks on dynamic market datasets.

Supported Data Sources:

OHLCV: open, high, low, and close prices; volume

adjusted_close: adjusted close price

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

Plug-and-Play (PnP)

In the development pipeline, we separate market environments from the data layer and the agent layer. A DRL agent can be directly plugged into our environments. Different agents/algorithms can be compared by running on the same benchmark environment for fair evaluations.

The following DRL libraries are supported:

• ElegantRL: Lightweight, efficient and stable DRL implementation using PyTorch.
• Stable-Baselines3: Improved DRL algorithms based on OpenAI Baselines.
• RLlib: An open-source DRL library that offers high scalability and unified APIs.

A demonstration notebook for plug-and-play with ElegantRL, Stable Baselines3 and RLlib: Plug and Play with DRL Agents

In addition to research-oriented DRL workflows, FinRL-Meta can serve as the market environment layer for broader ecosystem projects. For next-generation modular trading infrastructure and production deployment, see FinRL-X / FinRL-Trading.

"Training-Testing-Trading" Pipeline

We employ a training-testing-trading pipeline. First, a DRL agent is trained in a training dataset and fine-tuned (adjusting hyperparameters) in a testing dataset. Then, backtest the agent (on historical dataset), or depoy in a paper/live trading market.

This pipeline address the information leakage problem by separating the training/testing and trading periods.

Such a unified pipeline also allows fair comparisons among different algorithms.

Our Vision

For future work, we plan to build a multi-agent-based market simulator that consists of over ten thousands of agents, namely, a FinRL-Metaverse. First, FinRL-Metaverse aims to build a universe of market environments, like the XLand environment (source) and planet-scale climate forecast (source) by DeepMind. To improve the performance for large-scale markets, we will employ GPU-based massive parallel simulation just as Isaac Gym (source). Moreover, it will be interesting to explore the deep evolutionary RL framework (source) to simulate the markets. Our final goal is to provide insights into complex market phenomena and offer guidance for financial regulations through FinRL-Meta.

Citing FinRL-Meta

Dynamic Datasets and Market Environments for Financial Reinforcement Learning

@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 - Nature},
    year = {2024}
}

FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning

@article{finrl_meta_2022,
    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},
    title = {{FinRL-Meta}: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning},
    journal = {NeurIPS},
    year = {2022}
}

FinRL-Meta: Data-Driven Deep ReinforcementLearning in Quantitative Finance

@article{finrl_meta_2021,
    author = {Liu, Xiao-Yang and Rui, Jingyang and Gao, Jiechao and Yang, Liuqing and Yang, Hongyang and Wang, Zhaoran and Wang, Christina Dan and Guo Jian},
    title   = {{FinRL-Meta}: Data-Driven Deep ReinforcementLearning in Quantitative Finance},
    journal = {Data-Centric AI Workshop, NeurIPS},
    year    = {2021}
}

For the next-generation production-oriented trading stack in the FinRL ecosystem, please also see FinRL-X / FinRL-Trading.

Collaborators

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: [email protected]

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.