Sample mean based index policies by <i>O</i>(log <i>n</i>) regret for the multi-armed bandit problem (Q4862097)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Sample mean based index policies by O(log n) regret for the multi-armed bandit problem |
scientific article; zbMATH DE number 837042
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Sample mean based index policies by <i>O</i>(log <i>n</i>) regret for the multi-armed bandit problem |
scientific article; zbMATH DE number 837042 |
Statements
Sample mean based index policies by <i>O</i>(log <i>n</i>) regret for the multi-armed bandit problem (English)
0 references
9 July 1996
0 references
upper confidence bounds
0 references
asymptotically efficient
0 references
large deviations
0 references
stochastic adaptive control
0 references
non-Bayesian infinite horizon version
0 references
multi-armed bandit problem
0 references
Kullback-Leibler number
0 references
0.8774354
0 references
0.8609834
0 references
0.86094105
0 references
0 references
0.8567141
0 references
