Best-Arm Identification with Noisy Actuation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915910262980608 |
|---|---|
| author | Karakas, Merve Hanna, Osama Yang, Lin F. Fragouli, Christina |
| author_facet | Karakas, Merve Hanna, Osama Yang, Lin F. Fragouli, Christina |
| contents | In this paper, we consider a multi-armed bandit (MAB) instance and study how to identify the best arm when arm commands are conveyed from a central learner to a distributed agent over a discrete memoryless channel (DMC). Depending on the agent capabilities, we provide communication schemes along with their analysis, which interestingly relate to the zero-error capacity of the underlying DMC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02255 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Best-Arm Identification with Noisy Actuation Karakas, Merve Hanna, Osama Yang, Lin F. Fragouli, Christina Information Theory Machine Learning In this paper, we consider a multi-armed bandit (MAB) instance and study how to identify the best arm when arm commands are conveyed from a central learner to a distributed agent over a discrete memoryless channel (DMC). Depending on the agent capabilities, we provide communication schemes along with their analysis, which interestingly relate to the zero-error capacity of the underlying DMC. |
| title | Best-Arm Identification with Noisy Actuation |
| topic | Information Theory Machine Learning |
| url | https://arxiv.org/abs/2604.02255 |