Online Multi-Armed Bandits with Adaptive Inference
带自适应推断的在线多臂老虎机AI 解读 ↓
← 返回论文列表与筛选
阅读说明
本页整理公开书目信息，不生成学术质量评分。AI 解读根据题名及所注明的摘要或原文片段生成，未完成全文核验，可能有误；具体假设、证明与结论请核对原文。摘要保留来源文本，未经模型改写。
DOI 首次登记不等于接收或发表日期。部分更正、评论等条目没有独立摘要；缺少可靠材料时保留待补状态。
本页为预印本版本；arXiv 收录、作者填写的期刊信息以及作者既有发表经历，都不单独证明本篇已接收。作者发表记录按 OpenAlex 身份与完整姓名、本站覆盖期刊 ISSN 及正式卷期核对，只展示已核实例，档案仍可能误合并。
引用量采用 OpenAlex 单条关联记录，不合计多个记录；关联记录可能包含正式发表版本，不等于此版本单独引用。缺失不视为零，引用指标不代表论文质量。
关注作者按书目中的完整姓名匹配，同名和姓名变体需人工辨别。相关论文先按共享细分方向和具体方法排列，再参考通用方法与发表日期。
分类依据与纠错
AI 根据所提供的论文材料归类：摘要明确借助因果推断中的双重稳健估计，处理自适应选臂数据中的平均奖励推断。
反馈分类问题
正在核对关联版本…
代码、数据与补充材料
正在核对对应版本的资源…
带自适应推断的在线多臂老虎机
- 研究问题
- 多臂老虎机的自适应选臂产生非独立同分布数据时，如何改进各臂真实平均奖励的推断，并改善决策和最优臂识别表现？
- 方法与思路
- 作者提出双重自适应 Thompson 抽样，对各臂平均奖励的双重稳健估计项进行自适应重加权，结合推断与探索。
- 材料陈述的贡献
- 摘要称，DATS 在报告的实验中改善遗憾和识别最优臂的样本复杂度，并给出与 UCB、TS 相匹配至对数因子的有限期遗憾界。
- 阅读关注点
- 应核对自适应权重、双重稳健估计与 TS 更新的连接，奖励和探索条件，以及遗憾界与推断有效性各自依赖的假设。
- 阅读边界
- 这是 arXiv 预印本，同行评审或期刊接收未核实；摘要未说明完整奖励条件或数值幅度，实验优势不能推广到所有老虎机环境。
原文摘要
During online decision making in Multi-Armed Bandits (MAB), one needs to conduct inference on the true mean reward of each arm based on data collected so far at each step. However, since the arms are adaptively selected--thereby yielding non-iid data--conducting inference accurately is not straightforward. In particular, sample averaging, which is used in the family of UCB and Thompson sampling (TS) algorithms, does not provide a good choice as it suffers from bias and a lack of good statistical properties (e.g. asymptotic normality). Our thesis in this paper is that more sophisticated inference schemes that take into account the adaptive nature of the sequentially collected data can unlock further performance gains, even though both UCB and TS type algorithms are optimal in the worst case. In particular, we propose a variant of TS-style algorithms--which we call doubly adaptive TS--that leverages recent advances in causal inference and adaptively reweights the terms of a doubly robust estimator on the true mean reward of each arm. Through 20 synthetic domain experiments and a semi-synthetic experiment based on data from an A/B test of a web service, we demonstrate that using an adaptive inferential scheme (while still retaining the exploration efficacy of TS) provides clear benefits in online decision making: the proposed DATS algorithm has superior empirical performance to existing baselines (UCB and TS) in terms of regret and sample complexity in identifying the best arm. In addition, we also provide a finite-time regret bound of doubly adaptive TS that matches (up to log factors) those of UCB and TS algorithms, thereby establishing that its improved practical benefits do not come at the expense of worst-case suboptimality.