Stock markets have witnessed a surge in interest in automated trading systems, driven by their potential to enhance investment decisions and increase returns. This study explores the application of the Deep Q-Network (DQN) Trader, a reinforcement learning algorithm, in the domain of automated trading. The primary objective is to evaluate the efficacy and performance of the DQN Trader in real financial markets. The research delves into the theoretical foundations of DQN, implementation challenges, training, and evaluation methodologies, presenting comprehensive outcomes. The extensive numerical experiments on historical data sets of GOOGL, TSLA, AMZN, AAPL, and NSEI reveal that the DQN Trader exhibits a notable ability to generate profitable trading decisions. These outcomes provide valuable insights for both traders and researchers as the model gave a profit of 28% on the overall period, highlighting the model’s adaptability to dynamic market conditions and its potential contribution to automated trading strategies.