multi-armed bandit
reinforcement learning problem exemplifying the exploration–exploitation tradeoff
Facts
4 properties- Subclass of
- mathematical problem, optimization problem[2][3]
- Named after
- slot machine[1]
- Studied by
- probability theory[6]
🏷️ Also known as
en bandit problem
en K-armed bandit
en multi-armed bandit
en multi-armed bandit problem
en N-armed bandit
es bandido multibrazo
fa ماشین شانس چند اهرمه
fr bandit manchot
fr Bandit manchot (mathematiques)
fr Bandit Manchot (Mathématiques)
ja 多腕バンディット問題
ko 멀티 암드 밴딧
pt bandidos multiarmados
uk Багаторукий бандит
zh 多臂式吃角子老虎機
zh 多臂老虎机
zh-hant 多臂老虎機
🔖 Identifiers · 5
- OpenAlex ID
- C123197309
- Freebase ID
- /m/087186
- GitHub topic
- multi-armed-bandit
- Mathematics Subject Classification ID
- 91A20
- Microsoft Academic ID (discontinued)
- 123197309
🔗 Connections
Subclass of 2
Facet of 1
Named after 1
Studied by 1
Press Enter · cited answer in seconds