Reinforcement Learning (RL) is a branch of artificial intelligence that focuses on enabling systems to make sequential decisions by interacting with their environment. It is based on the concept of reward and punishment, where an agent learns to choose actions that maximize cumulative rewards over time. Unlike supervised learning, RL does not rely on labeled data; instead, it learns through trial and error. The core components include the agent, environment, states, actions, and rewards. The main objective is to learn an optimal policy that determines the best action in each state. Among the most common algorithms are Q-Learning and Deep Q-Networks (DQN), which integrate deep neural networks with reinforcement learning to handle complex environments. This advancement has expanded RL applications across various domains. In robotics, RL enables adaptive motion control and intelligent interaction with dynamic surroundings. In healthcare, it is used to optimize treatment planning and personalized medicine. It also contributes to autonomous driving systems and traffic optimization. In the gaming field, reinforcement learning achieved significant milestones. A well-known example is AlphaGo, developed by DeepMind, which defeated the world champion of Go in 2016. Additionally, RL is applied in financial trading strategies and recommendation systems to enhance user experience. Despite challenges such as high computational demands and long training times, reinforcement learning remains one of the most promising and rapidly evolving areas in artificial intelligence. An advanced extension of reinforcement learning is Deep Reinforcement Learning, which combines deep neural networks with interactive decision-making mechanisms, enabling systems to process high-dimensional data such as images and video streams. RL has also shown promising applications in smart energy management, resource optimization in data centers, and even drug discovery and molecular design. With the advancement of cloud computing and powerful GPUs, training reinforcement learning models has become more efficient .