We study decision making in environments where the reward is only partially observed, but can be modeled as a function of an action and an observed context. This setting, known as contextual bandits, encompasses a wide variety of applications including health-care policy and Internet advertising. A central task is evaluation of a new policy given historic data consisting of contexts, actions and received rewards. The key challenge is that the past data typically does not faithfully represent proportions of actions taken by a new policy. Previous approaches rely either on models of rewards or models of the past policy. The former are plagued by a large bias whereas the latter have a large variance. We leverage the strength and overcome the weaknesses of the two approaches by adapting doubly robust estimation techniques to the problems of policy evaluation and optimization. We prove that this approach yields unbiased (and often lower variance) value estimates when we have either a good model of rewards or a good model of past policy. Extensive empirical comparison demonstrate that the doubly robust technique uniformly improves existing techniques, achieving both lower variance in value estimation and better policies. As such, we expect the doubly robust approach to become common practice.

在具有上下文情境和目标函数的决策环境中，我们使用双重稳健技术评估新策略，并证明这种方法使价值估计具有较低的方差，且能达到更好的策略，为该领域提供一种有效的方法。

双重稳健策略评估与学习