The rapid growth of algorithmic trading and financial artificial intelligence has motivated the search for adaptive, data-driven decision-making techniques that can outperform traditional trading strategies. This paper investigates the application of Q-learning, a value-based reinforcement learning algorithm, to stock trading and portfolio management. The trading process is modelled as a Markov Decision Process, where states represent market indicators and technical signals, actions correspond to buy, sell, or hold decisions, and rewards are defined in terms of risk-adjusted returns. Using historical stock data obtained from the Yahoo Finance API, Q-learning agent is implemented and backtested against benchmark strategies such as Buy-and-Hold and Random trading. Experimental results demonstrate that the Q-learning framework can achieve competitive performance, with higher cumulative returns and improved Sharpe ratios, while also adapting to dynamic market conditions. The study contributes to the literature by providing a systematic implementation of Q-learning in financial markets, highlighting both its strengths and limitations. Furthermore, challenges such as data non-stationarity, sample efficiency, and risk management are discussed, while outlining potential extensions to advanced methods like Deep Q-Networks and Actor-Critic models. The findings underscore the potential of reinforcement learning as a promising paradigm for intelligent financial decision-making and provide valuable insights for traders, researchers, and policymakers.