The optimization of power distribution network planning is crucial for enhancing the efficiency and reliability of electrical power delivery to consumers. As demand for electricity grows and systems become more complex, traditional planning methods often fall short in achieving optimal configurations. Deep Reinforcement Learning (DRL), a dynamic branch of artificial intelligence, has shown promise in solving complex optimization problems by learning optimal actions through trial-and-error interactions with the environment. This paper explores the application of DRL in distribution network expansion planning. By simulating different network configurations and operational strategies, a DRL agent can potentially discover novel and efficient solutions that traditional methods may overlook. The case studies demonstrate how DRL can be employed to optimize network topologies, reduce operational costs in response to varying demand and supply conditions.