This course introduces the fundamentals of reinforcement learning (RL), where software agents learn optimal actions through trial and error to achieve a long-term goal. You will break down the core RL framework of agents, environments, states, actions, and rewards, and understand how they interact in a feedback loop. We will explore how these agents develop strategies, or policies, to maximize cumulative reward, such as enhancing network throughput or balancing traffic load. The curriculum covers key algorithms that enable machines to learn from the consequences of their actions rather than from static datasets. This approach is pivotal for creating adaptive systems that can operate dynamically in complex and changing environments. You will finish with a foundational understanding of how to apply RL principles to real-world telecom challenges like resource allocation and autonomous network control.