Latent Bandits.

Abstract : We consider a multi-armed bandit problem where the reward distributions are indexed by two sets --one for arms, one for type-- and can be partitioned into a small number of clusters according to the type. First, we consider the setting where all reward distributions are known and all types have the same underlying cluster, the type's identity is, however, unknown. Second, we study the case where types may come from different classes, which is significantly more challenging. Finally, we tackle the case where the reward distributions are completely unknown. In each setting, we introduce specific algorithms and derive non-trivial regret performance. Numerical experiments show that, in the most challenging agnostic case, the proposed algorithm achieves excellent performance in several difficult scenarios.
Document type :
Other publications
Complete list of metadatas

https://hal.inria.fr/hal-00926281
Contributor : Odalric-Ambrym Maillard <>
Submitted on : Thursday, January 9, 2014 - 1:03:01 PM
Last modification on : Sunday, December 31, 2017 - 9:44:02 AM
Long-term archiving on : Thursday, April 10, 2014 - 3:05:19 PM

File

icml_cr_Arxiv.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00926281, version 1

Citation

Odalric-Ambrym Maillard, Shie Mannor. Latent Bandits.. 2014. ⟨hal-00926281⟩

Share

Metrics

Record views

368

Files downloads

379