the.ai

Reinforcement / Methods

verified

Q-Learning

Learn a number for every state-action pair saying how good that action is there, and always update as though you will act optimally afterwards — even when you did not. That gap is the point: it lets an agent learn the best policy while behaving badly enough to explore, which is why it was the first method to feel like it could learn anything.

Viz primitive · budget-splitreplayed-updates = 24

replayed-updates holds 75% of the budget; rest holds the remaining 25%.

Updates drawn from the replay buffer against those taken from the episode just played, in updates. Drag the replay ratio to watch consecutive samples stop dominating what is learned from.

24

Reviewed by opendroid · 2026-08-17

Origin · not linkable

  • Watkins & Dayan 1992 — Q-learning · Machine Learning 8(3) · doi:10.1007/BF00992698