Reinforcement learning is a subfield of artificial intelligence focused on learning through repeated interactions with an environment. It forms the foundation for state-of-the-art algorithms used in strategy games such as Chess, Go, Backgammon, and Starcraft, as well as in diverse applications across robotics, operations research, and various engineering disciplines. This course covers the fundamental algorithms of reinforcement learning, with an emphasis on understanding the underlying principles, implementing the methods, and benchmarking their performance.