Batched Bandit Problems
Motivated by practical applications, chiefly clinical trials, we study the regret achievable for stochastic bandits under the constraint that the employed policy must split trials into a small number of batches. Our results show that a very small number of batches gives close to minimax optimal regr...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Mathematical Statistics
2015
|
| Online Access: | http://hdl.handle.net/1721.1/98879 https://orcid.org/0000-0002-0135-7162 |
| Summary: | Motivated by practical applications, chiefly clinical trials, we study the regret achievable for stochastic bandits under the constraint that the employed policy must split trials into a small number of batches. Our results show that a very small number of batches gives close to minimax optimal regret bounds. As a byproduct, we derive optimal policies with low switching cost for stochastic bandits. |
|---|