AI engineering glossary · Reinforcement learning
What is regret?
Regret: The gap between the total score that the best fixed option would have earned and the score actually earned over a number of rounds. Lower growth of this gap means faster learning. Good bandit methods have regret growing only logarithmically with the number of rounds.
Regret: an example
If the best banner would have earned 500 clicks in 10,000 views but the learner got 460, its regret is 40 clicks.
Related terms
More Reinforcement learning terms
- Reinforcement learning
- Return
- Reward
- Reward function
- Reward shaping
- Sample efficiency
- SARSA
- Score function estimator
Where you learn it
Regret is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.