Trading off rewards and errors in multi-armed bandits
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910183576305664 |
|---|---|
| author | Erraqabi, Akram Lazaric, Alessandro Valko, Michal Brunskill, Emma Liu, Yun-En |
| author_facet | Erraqabi, Akram Lazaric, Alessandro Valko, Michal Brunskill, Emma Liu, Yun-En |
| contents | In multi-armed bandits, the most-explored arms are the most informative, while reward maximization typically pulls only the best arm. We study the tradeoff between identifying arm means accurately and accumulating reward, and present an algorithm with regret guarantees that interpolates between the two objectives. We provide both upper and lower bounds and validate empirically. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00488 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Trading off rewards and errors in multi-armed bandits Erraqabi, Akram Lazaric, Alessandro Valko, Michal Brunskill, Emma Liu, Yun-En Machine Learning In multi-armed bandits, the most-explored arms are the most informative, while reward maximization typically pulls only the best arm. We study the tradeoff between identifying arm means accurately and accumulating reward, and present an algorithm with regret guarantees that interpolates between the two objectives. We provide both upper and lower bounds and validate empirically. |
| title | Trading off rewards and errors in multi-armed bandits |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.00488 |