Reinforcement Learning (RL) has become a significant subject in Artificial Intelligence (AI), allowing systems to learn and adapt by interacting with their environment. This resembles how humans and animals learn through trial and error. RL helps machines improve their decision making by responding to rewards and penalties. What once seemed nearly impossible, like mastering video games using only raw pixel data, is now achievable through deep reinforcement learning. In fact, RL agents can outperform humans in complex tasks, often without direct supervision. In this chapter, we explore the latest developments in RL, including model-based methods, policy optimization techniques, and real-world deployments.