Reinforcement learning

AIGP glossary · Last reviewed: 2026-07-08 · By Victor Humenhuk (AIGP certified)

Reinforcement learning - An agent learns by trial and error in an environment, maximising reward via reinforcement and penalties.

In the AIGP body of knowledge, Reinforcement learning comes up under Module 1: Foundations of AI · BoK IV.A; Module 8: AI Governance Vocabulary.

Reinforcement learning in context

• ==Label availability is the sorting key==: supervised uses labelled pairs, unsupervised finds structure in unlabelled data, semi-supervised blends both, and reinforcement learning optimises for reward. (Machine learning families)

Where Reinforcement learning is covered in the AIGP study notes

• The four ways machines learn
• Machine learning families

Related terms

• Supervised learning
• Unsupervised learning
• Semi-supervised learning
• Classification models
• Regression models
• Clustering
• Association rule learning
• SVM (Support Vector Machine)
• SVR (Support Vector Regression)
• Machine learning

Test yourself on Reinforcement learning

Recognising a definition is not the same as applying it in an exam scenario. Work through the free AIGP practice questions, or read the full AIGP study guide - every study note is free.

← Back to the AIGP glossary