This repository contains a reinforcement learning-based agent designed to navigate the stock market effectively. The agent learns to make trading decisions by training on historical stock price data.
Follow these steps to set up and use the RL stock trading agent:
-
Fetch Historical Data
- Execute
python data-fetch.pyto fetch historical data for your desired stock. Replace the stock symbol and date range with your preferences in the script.
python data-fetch.py
This script retrieves historical stock price data, which will be used for training and testing the model.
- Next, run TradingEnv.py to train the reinforcement learning model using the fetched data. Ensure that you have all the required dependencies installed (see requirements.txt).
python TradingEnv.py
- Execute
-
Using a Pretrained Model Alternatively, this repository provides a custom trained model (trading_agent.zip) that you can load and use directly if you prefer not to train your own model.
-
Testing the Model with Live Data Run TestTradingEnv.py to evaluate the accuracy of the trained model when making trading decisions on live data.
python TestTradingEnv.py- Render the model This custom trained model can be rendered by running the renderscript
python renderscript.py
- Open AI gym reference docs: https://gymnasium.farama.org/
- Feel free to explore and adapt the code to your specific needs in stock trading and reinforcement learning.