This thesis investigates the use of reinforcement learning algorithms for optimizing the purchase and sale of energy produced by a renewable energy plant in real-time. The study explores the effectiveness of different reinforcement learning algorithms in achieving optimal energy trading strategies, considering different environmental and economic factors. The goal is to build an environment as close to reality as possible and investigate the use of algorithms that can process and refine trading techniques. The study is expected to provide valuable insights into the potential of using intelligent algorithms to optimize trading in intraday electricity markets.