论文标题
令人振奋的土匪
Uplifting Bandits
论文作者
论文摘要
我们介绍了一个多武器的强盗模型，其中奖励是多个随机变量的总和，每个动作只会改变其中一些分布。每次动作之后，代理都会观察所有变量的实现。该模型是由营销活动和推荐系统激励的，在该系统中，变量代表了单个客户的结果，例如点击。我们提出了UCB风格的算法，以估计基线上的动作的提升。我们研究了问题的多种变体，包括何时未知基线和受影响的变量，并证明所有这些变量均具有sublritear后悔界限。我们还提供了较低的界限，以证明我们的建模假设的必要性是合理的。关于合成和现实世界数据集的实验显示了估计不使用这种结构的策略的振奋方法的方法。
We introduce a multi-armed bandit model where the reward is a sum of multiple random variables, and each action only alters the distributions of some of them. After each action, the agent observes the realizations of all the variables. This model is motivated by marketing campaigns and recommender systems, where the variables represent outcomes on individual customers, such as clicks. We propose UCB-style algorithms that estimate the uplifts of the actions over a baseline. We study multiple variants of the problem, including when the baseline and affected variables are unknown, and prove sublinear regret bounds for all of these. We also provide lower bounds that justify the necessity of our modeling assumptions. Experiments on synthetic and real-world datasets show the benefit of methods that estimate the uplifts over policies that do not use this structure.
