This chapter provides a comprehensive overview of reinforcement learning (RL), a paradigm in which agents learn to make decisions through interaction with their environment. It begins by outlining the reinforcement learning process, including key components such as agents, environments, rewards, and policies. The chapter then explores various RL approaches, including model-free and model-based methods, and introduces deep reinforcement learning, which leverages neural networks to handle high-dimensional state and action spaces. The advantages of RL, such as its ability to learn optimal behaviour through trial and error, are discussed alongside its challenges, including sample inefficiency, instability, and exploration-exploitation trade-offs. The chapter also addresses planning under uncertainty, where agents must make decisions with incomplete or probabilistic information. Additional topics include transfer learning, which enables knowledge reuse across tasks, and reinforcement learning from human feedback (RLHF), a growing area that incorporates human preferences to guide agent behaviour.