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

Paper recorded by Signals 4 on 2026-10-15 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-15 on arXiv · recorded by Signals 4 on 2026-10-16

Category: cs.LG · 机器学习 · first seen 2026-10-16

Abstract

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 prob

Read on arXiv →