Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles
A fundamental challenge in contextual bandits is to develop flexible, general-purpose algorithms with computational requirements no worse than classical supervised learning tasks such as classification and regression. Algorithms based on regression have shown promising empirical success, but theoret...
| Huvudupphovsmän: | , |
|---|---|
| Övriga upphovsmän: | |
| Materialtyp: | Artikel |
| Språk: | English |
| Publicerad: |
2021
|
| Länkar: | https://hdl.handle.net/1721.1/138306 |