The final dataset utilised for the publication "Investigating Reinforcement Learning Approaches In Stock Market Trading" was processed by downloading and combining data from multiple reputable sources to suit the specific needs of this project. Raw data were retrieved by downloading them using a Python finance API. Afterwards, Python and NumPy were used to combine and normalise the data to create the final dataset.The raw data was sourced as follows:Stock Prices of NVIDIA & AMD, Financial Indexes, and Commodity Prices: Retrieved from Yahoo Finance.Economic Indicators: Collected from the US Federal Reserve.The dataset was normalised to minute intervals, and the stock prices were adjusted to account for stock splits.This dataset was used for exploring the application of reinforcement learning in stock market trading. After creating the dataset, it was used in s reinforcement learning environment to train several reinforcement learning algorithms, including deep Q-learning, policy networks, policy networks with baselines, actor-critic methods, and time series incorporation. The performance of these algorithms was then compared based on profit made and other financial evaluation metrics, to investigate the application of reinforcement learning algorithms in stock market trading.The attached 'README.txt' contains methodological information and a glossary of all the variables in the .csv file.