Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems (Q5396763)
From MaRDI portal
scientific article; zbMATH DE number 6254309
Language | Label | Description | Also known as |
---|---|---|---|
English | Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems |
scientific article; zbMATH DE number 6254309 |
Statements
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems (English)
0 references
3 February 2014
0 references
learning and statistical methods
0 references
game-theoretic learning
0 references
online learning
0 references
optimization
0 references
reinforcement learning
0 references