Reinforcement learning is a type of machine learning where an agent learns to make decisions by receiving rewards or penalties. It aims to maximize cumulative rewards through trial and error.

A process of analysing and deconstructing an existing AI system to help users understand how the system makes decisions particularly when dealing with black box models.

Rule-based systems use predefined rules to make decisions or solve problems. These systems follow a set of "if-then" statements to process information and reach conclusions. Unlike modern AI, they do not learn from data but rely on logical instructions set by humans.