Reinforcement learning

Also written: RL

Learning by trial and error from a reward signal, rather than from right answers.

Other terms from the same lesson

• accuracy: The share of predictions that were right. Misleading when one answer is much more common than the others.
• churn: Customers leaving: a customer who stops buying has churned. Predicting churn is the running example in Phase 3.
• machine learning: Getting a computer to learn a pattern from examples instead of writing the rules by hand.
• model: The thing that learns: a formula with adjustable numbers that turns inputs into predictions.
• self-supervised learning: Learning from data that supplies its own answers, such as hiding the next word of a sentence and guessing it. It's how language models are pretrained.
• unsupervised learning: Finding patterns, such as groups of similar customers, in data that has no right answers attached.