AI engineering glossary · Reinforcement learning
What is epsilon-greedy?
Epsilon-greedy: A simple exploration method: with probability epsilon pick a random choice, otherwise pick the one with the highest estimated value. Epsilon is often reduced over training so that behaviour becomes more greedy as knowledge improves.
Epsilon-greedy: an example
With epsilon = 0.1 and 4 options, the best-looking option is chosen with probability 0.9 + 0.1/4 = 0.925.
Related terms
More Reinforcement learning terms
- Experience replay
- Exploitation
- Exploration
- Exploration-exploitation trade-off
- Function approximation
- Goal-conditioned reinforcement learning
- Greedy policy
- Hierarchical reinforcement learning
Where you learn it
Epsilon-greedy is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.