Warm Starting Bandits with Side Information from Confounded Data
Warm Starting Bandits with Side Information from Confounded Data
复制标题
热启动强盗与来自混杂数据的辅助信息
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
S. Shakkottai
中科院分区：
文献类型：
--
作者：
Nihal Sharma;S. Basu;Karthikeyan Shanmugam;S. Shakkottai
我们研究了一个变种的多臂强盗问题的边信息的形式提供的平均值的界限。我们描述了如何这些界限的手段可以有效地用于热启动土匪。具体来说，我们提出了新的UCB-SI算法，并说明了改进的累积遗憾的标准UCB算法，理论和经验，在存在非平凡的边信息。如（Zhang & Bareinboim，2017）中所述，例如，当我们先前记录了关于武器的数据时，会出现此类信息，但这些数据是根据一项政策收集的，该政策的武器选择是基于不再可用的潜在变量。我们进一步提供了一种新的方法，在一些温和的假设下，从先前的部分混杂数据获得这样的界限。我们通过对来自真实的数据集的数据进行半合成实验来验证我们的发现。
We study a variant of the multi-armed bandit problem where side information in the form of bounds on the mean of each arm is provided. We describe how these bounds on the means can be used efficiently for warm starting bandits. Specifically, we propose the novel UCB-SI algorithm, and illustrate improvements in cumulative regret over the standard UCB algorithm, both theoretically and empirically, in the presence of non-trivial side information. As noted in (Zhang & Bareinboim, 2017), such information arises, for instance, when we have prior logged data on the arms, but this data has been collected under a policy whose choice of arms is based on latent variables to which access is no longer available. We further provide a novel approach for obtaining such bounds from prior partially confounded data under some mild assumptions. We validate our findings through semi-synthetic experiments on data derived from real datasets.
DOI：
10.1214/14-sts499
发表时间：
2014-11
期刊：
Statistical science : a review journal of the Institute of Mathematical Statistics
影响因子：
--
作者：
Richardson A;Hudgens MG;Gilbert PB;Fine JP
通讯作者：
Fine JP