multi-armed bandit
Sign in to saveAlso known as multi-armed bandit problem, K-armed bandit, N-armed bandit, bandit problem
reinforcement learning problem exemplifying the exploration–exploitation tradeoff
Wikidata facts
- Subclass of
- optimization problem
- Named after
- slot machine
Show 2 more facts
- studied by
- probability theory
- facet of
- game theory
via Wikidata · CC0