Papers
Topics
Authors
Recent
Search
2000 character limit reached

Explore Once, Evaluate Many: Multiple Policy Evaluation for Stochastic Linear Bandits

Published 15 Oct 2026 in cs.LG and stat.ML | (2610.22252v1)

Abstract: We study how to evaluate KK target policies simultaneously in stochastic contextual bandits with linear reward structure. Given a known dd-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 ε\varepsilon with probability at least $1-δ$. The algorithm uses O~ ⁣((L2S2+β2)(1∨ρ⋆)ε2⋅log⁡(K))\widetilde{\mathcal{O}}\!\left( \frac{(L^2S^2+β^2)(1\veeρ^\star)}{\varepsilon^2} \cdot \log(K) \right) context draws and reward observations, where ρ⋆≤dρ^\star\le d is an instance-dependent measure of the difficulty of designing a shared sampling distribution. Here, LL, SS, and ββ bound the feature norm, reward parameter norm, and reward noise, respectively, and the suppressed factors are logarithmic in KK, dd, and $1/δ$. 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 ρ⋆ρ^\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 KK queries per shared planning context.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.