AI engineering glossary · Reinforcement learning
What is multi-armed bandit?
Multi-armed bandit (also called Bandit problem): The simplest setting for studying the balance of trying and exploiting: several options, each paying a random reward with an unknown average, and no changing situation. The learner repeatedly picks one option to maximise total payoff.
Multi-armed bandit: an example
Three banner designs with unknown click rates of 2, 3 and 5 percent; the learner must find the 5 percent one while wasting few impressions.
Related terms
More Reinforcement learning terms
- MuZero
- n-step return
- Nash equilibrium
- Natural policy gradient
- Noisy networks
- Off-policy
- Off-policy evaluation
- Offline reinforcement learning
Where you learn it
Multi-armed bandit is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.