Foundations intermediate

Reinforcement Learning

Also called: RL

Learning by trial and error, guided by rewards rather than labelled answers.

A reinforcement learning agent acts in an environment, observes what happens, and receives a reward signal. Over many episodes it learns a policy that maximises expected reward. RL is behind game-playing systems and, in modified form, behind the alignment step in modern chat models.

In practice: An agent learns to play a game with no rules explained — only a score that goes up or down.

Where this comes up