预印本前沿

收录说明

收录范围: 保留计量方法研究、相关统计基础，以及实质涉及计量方法的应用、教程、比较和综述。书评、刊务及明确无关内容不公开；身份或相关性证据不足的记录保留待核，补充可靠材料后可重新判断。; 预印本来自 arXiv 计量经济学及相关统计、金融分类和主题检索。主题检索从 2021 年起回补；关注作者追溯更早年份，部分历史文献按已核验编号补录。收录不表示通过同行评审，仍可能遗漏。; 本库首次提交范围：2004-06-23 — 2026-10-14。
阅读范围: 默认显示本库全部预印本。可选“优先阅读”：至少一位作者同时满足有可核验的本站覆盖期刊正式发表记录，且 OpenAlex 总引用超过 1,000 次。按同一作者身份匹配，两项缺一不可。此筛选提供阅读线索，不作为论文质量判断。
日期与排序: 默认按最近修订排序；年份和日期筛选使用首次提交时间。同一 arXiv 编号的修订会合并。仅有月份或年份时，日期区间相交也会纳入。
分类与引用: 领域和方法依据题名、摘要初步分类，可人工修正；分类不代表论文质量。引用数采用 OpenAlex 单条关联记录，不合计版本。
更新与 AI 解读: 正常题录、可靠摘要与引用同步继续；日、周、月简报按核实的发表与修订日期汇总，历史补录保留在文献库。AI 解读依据可靠摘要或已核实原文片段，已有解读保留供阅读参考；缺少可靠材料的条目保持待解读，浏览页面不会触发生成。

最近同步 10/16 00:32

1 篇论文

导出

BibTeX ↓RIS ↓RSS 订阅 ↗

Towards a Sharp Analysis of Offline Policy Learning for $f$ -Divergence-Regularized Contextual BanditsTowards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits

Qingyue Zhao · Kaixuan Ji · Heyang Zhao · Tong Zhang · Quanquan Gu首次提交 2025-02-09 · 修订 2026-02-26 · v3arXiv预印本

面向 f-散度正则化上下文赌博机的离线策略学习精确分析AI 解读

Many offline reinforcement learning algorithms are underpinned by $f$ -divergence regularization, but their sample complexity *defined with respect to regularized objectives* still lacks tight analyses, especially in terms of concrete data coverage conditions. In this paper, we study the exact concentrability requirements to achieve the $\tildeΘ(ε^{-1})$ sample complexity for offline $f$ -divergence-regularized contextual bandits. For reverse Kullback-Leibler (KL) divergence,…Many offline reinforcement learning algorithms are underpinned by $f$-divergence regularization, but their sample complexity *defined with respect to regularized objectives* still lacks tight analyses, especially in terms of concrete data coverage conditions. In this paper, we study the exact concentrability requirements to achieve the $\tildeΘ(ε^{-1})$ sample complexity for offline $f$-divergence-regularized contextual bandits. For reverse Kullback-Leibler (KL) divergence,…

正则化与变量选择

关联记录被引 0 次 ↗OpenAlex · 核验 2026-10-14

AI 解读阅读原文 ↗BibTeX ↓

Towards a Sharp Analysis of Offline Policy Learning for fff-Divergence-Regularized Contextual BanditsTowards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits

Towards a Sharp Analysis of Offline Policy Learning for $f$ -Divergence-Regularized Contextual BanditsTowards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits