Supervised, Unsupervised and Reinforcement Learning Explained

By QuizMaster Learn Team, 2026-10-27

Machine learning is a way of building programs that learn patterns from data instead of following hand-written rules. Most methods fall into three families, depending on the kind of feedback the program receives.

Supervised learning

In supervised learning the data comes with correct answers, called labels. The model learns the relationship between inputs and labels and then predicts labels for new inputs. Examples include detecting spam email, which is a classification task, and predicting house prices, which is a regression task.

Unsupervised learning

Here there are no labels. The model looks for structure on its own. Clustering is the best-known example: a shop might group customers with similar buying habits without being told in advance what the groups should be. It is also used to simplify data and to find unusual items.

Reinforcement learning

In reinforcement learning an agent learns by trying actions and receiving rewards or penalties. Over many attempts it discovers which actions lead to the best long-term result. This approach is used to train game-playing programs and in some robotics tasks.

Choosing between them

• Do you have labelled examples? Use supervised learning.
• Do you only have raw data and want to discover groups or patterns? Use unsupervised learning.
• Does a program need to make a sequence of decisions and learn from outcomes? Consider reinforcement learning.

Two ideas to remember

Whatever the type, a model must be tested on data it has not seen before. A model that scores very well on its training data but poorly on new data is overfitting. Try the Machine Learning Basics and Machine Learning Concepts quizzes to check your understanding.