Thompson Sampling for the non-Stationary Corrupt Multi-Armed Bandit
Résumé
We propose an extension of the corrupt multi-armed bandit problem proposed in Gajane et al. (2018) where the distributions of reward and feedback are non-stationary. We also propose an extension with three variants of the Global Switching Thompson Sampling proposed in Mellor and Shapiro (2013) for the corrupted setting. This extension is based on the aggregation of a growing number of experts seen as learners. Finally, we conduct experiments providing evidences that in practice our proposal compares favorably with the oracle that exactly knows the location of the environment changes.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |