Metraipolis › archive › dc_2dcff60b8eaa
Trading off rewards and errors in multi-armed bandits — arXiv:2605.00488
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2605.00488
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T09:33:24.275Z
- SHA-256 of the archived text
176573c77e6aeca78d6ae85bdf6280a38a6b7a6679cda58014124f6ee9848bfd- Stable URL of this page
https://metraipolis.com/documento/dc_2dcff60b8eaa
How to cite
Trading off rewards and errors in multi-armed bandits — arXiv:2605.00488 — arXiv (en), https://arxiv.org/abs/2605.00488 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2dcff60b8eaa (Metraipolis archive dc_2dcff60b8eaa, sha256 176573c77e6aeca78d6ae85bdf6280a38a6b7a6679cda58014124f6ee9848bfd)
BibTeX
@misc{dc2dcff60b8eaa,
title = {Trading off rewards and errors in multi-armed bandits — arXiv:2605.00488},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2605.00488},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2dcff60b8eaa; sha256 176573c77e6aeca78d6ae85bdf6280a38a6b7a6679cda58014124f6ee9848bfd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2605.00488. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2605.00488 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T08:24:13.971Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).