Metraipolis › archive › dc_0c0fb6d663bd
Explore Once, Evaluate Many: Multiple Policy Evaluation for Stochastic Linear Bandits — arXiv:2610.22252
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22252
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:24:50.830Z
- SHA-256 of the archived text
d4a0bbabbbdb29b2bdb4f646ea7cdceb7f57bba7d60b647da6720bedf4a5afe9- Stable URL of this page
https://metraipolis.com/documento/dc_0c0fb6d663bd
How to cite
Explore Once, Evaluate Many: Multiple Policy Evaluation for Stochastic Linear Bandits — arXiv:2610.22252 — arXiv (en), https://arxiv.org/abs/2610.22252 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0c0fb6d663bd (Metraipolis archive dc_0c0fb6d663bd, sha256 d4a0bbabbbdb29b2bdb4f646ea7cdceb7f57bba7d60b647da6720bedf4a5afe9)
BibTeX
@misc{dc0c0fb6d663bd,
title = {Explore Once, Evaluate Many: Multiple Policy Evaluation for Stochastic Linear Bandits — arXiv:2610.22252},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22252},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0c0fb6d663bd; sha256 d4a0bbabbbdb29b2bdb4f646ea7cdceb7f57bba7d60b647da6720bedf4a5afe9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22252. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study how to evaluate $K$ target policies simultaneously in stochastic contextual bandits with linear reward structure. Given a known $d$-dimensional feature map and reward-free access to policy queries, we propose PRISMA (Policy evaluation through Regularized Information Sharing and Mixture Allocation), an algorithm that estimates every target policy's value to accuracy $\varepsilon$ with probability at least $1-\delta$. The algorithm uses $\widetilde{\mathcal{O}}\!\left( \frac{(L^2S^2+\beta^2)(1\vee\rho^\star)}{\varepsilon^2} \cdot \log(K) \right)$ context draws and reward observations, where $\rho^\star\le d$ is an instance-dependent measure of the difficulty of designing a shared sampling distribution. Here, $L$, $S$, and $\beta$ bound the feature norm, reward parameter norm, and reward noise, respectively, and the suppressed factors are logarithmic in $K$, $d$, and $1/\delta$. Our method combines reward-free planning, a regularized sampling design, and a single ridge regression estimator shared across all target policies. An adaptive doubling procedure selects the regularization scale without knowledge of $\rho^\star$. The guarantees require no numerical lower bound on second-moment eigenvalues and have no explicit dependence on the cardinalities of the context and action spaces. Policy-query costs are accounted for separately, with $K$ queries per shared planning context.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.22252 — 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 2026-10-16T08:48:02.805Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).