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...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2021-12-03T15:09:50Z.
|
| Subjects: | |
| Online Access: | Get fulltext |