Epsilon-Greedy

AI and Machine Learning · Reinforcement Learning · also: ε-greedy · epsilon-greedy.yaml

Take the best action known, except on an ε fraction of steps where the action is uniformly random. The cheapest exploration that still visits every action infinitely often, and the baseline anything cleverer has to beat.

• supersedescorrects · extends
• classifiesspecializes · part-of
• substitutes forapproximates · alternative-to
• depends onrequires · validates

Colour is the family; a dashed line is the second member of it.

This node

• correctsfixes a defect in Q-Learningacting greedily never revisits an action its first sample underrated
• part-ofis a subtopic of Multi-Armed Bandit

Referenced by

• correctsIntrinsic Motivation fixes a defect in thisrandom actions never chain into the long sequence a sparse reward needs
• correctsUpper Confidence Bound fixes a defect in thisuniform exploration keeps re-trying arms already measured as bad

References

• Reinforcement Learning: An Introduction — Sutton, Barto — 2018 · link
• Background — Multi-armed bandit on Wikipedia