Skip to content
All library documents

FinRL Stock Trading Workflow with Deep Reinforcement Learning

Article FinRL

Summary

This introductory page presents FinRL as a framework for applying deep reinforcement learning to stock trading. It directs readers to a sequence of example notebooks covering data preparation, model training, and backtesting, framing them as a way to follow the workflow from raw market data to strategy evaluation. A separate tutorial notebook is also suggested for running the material in a hosted notebook environment.

The page connects the example to a 2018 paper on practical deep reinforcement learning for stock trading and displays a result image from that work. It offers a learning path and points to a research reference, but the page itself does not explain the trading environment, state and action design, reward function, algorithms, or evaluation assumptions. The result image is not accompanied here by numerical detail or discussion of limitations, so readers need the notebooks and cited paper to assess the method and its evidence.

Key ideas

  • FinRL presents deep reinforcement learning as an approach to stock trading.
  • Its suggested workflow separates data preparation, model training, and backtesting.
  • The examples are associated with a 2018 research paper on practical deep RL trading.
  • The introductory page itself does not specify the model design or evaluation assumptions.
  • The displayed result requires further context from the notebooks or paper to assess.

Tags

EquitiesMachine learningBacktesting
Full text
# first glance


:github_url: https://github.com/AI4Finance-Foundation/FinRL

First Glance
============================

To quickly understand what is FinRL and how it works, you can go through the series Stock_NeurIPS2018, including *Stock_NeurIPS2018_Data.ipynb*, *Stock_NeurIPS2018_Train.ipynb*, *Stock_NeurIPS2018_Backtest.ipynb* in our examples directory (https://github.com/AI4Finance-Foundation/FinRL/tree/master/examples)

This is how we use Deep Reinforcement Learning for Stock Trading from scratch.


.. tip::

    Run the code step by step at `Google Colab`_.

    .. _Google Colab: https://colab.research.google.com/github/AI4Finance-Foundation/FinRL-Tutorials/blob/master/1-Introduction/Stock_NeurIPS2018_SB3.ipynb

The notebook and the following result is based on our paper *Practical deep reinforcement learning approach for stock trading* Xiong, Zhuoran, Xiao-Yang Liu, Shan Zhong, Hongyang Yang, and Anwar Walid. "Practical deep reinforcement learning approach for stock trading." arXiv preprint arXiv:1811.07522 (2018).

.. image:: ../image/result_NeurIPS.png
   :width: 80%
   :align: center

Shown in full with attribution under the source's licence. Licence: MIT

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.