Finite-time Upper Bounds for the Multi-armed Bandit Problem with Bounded Rewards |
Paul Fischer, N. Cesa-Bianchi
|
| Type | Conference paper [With referee] |
| Conference | Proc. 15th International Conference on Machine Learning (ICML98) |
| Year | 1998 pp. 100-108 |
| BibTeX data | [bibtex] |
| IMM Group(s) | Computer Science & Engineering, Other |