Partial monitoring is an expressive framework for sequential decision-making with an abundance of applications, including graph-structured and dueling bandits, dynamic pricing and transductive feedback models. We survey and extend recent results on the linear formulation of partial monitoring that naturally generalizes the standard linear bandit setting. The main result is that a single algorithm, information-directed sampling (IDS), is (nearly) worst-case rate optimal in all finite-action games. We present a simple and unified analysis of stochastic partial monitoring, and further extend the model to the contextual and kernelized setting.

翻译：部分监控是一个富有表现力的序贯决策框架，具有丰富的应用场景，包括图结构赌博机、对抗性赌博机、动态定价以及转导反馈模型。本文综述并扩展了线性部分监控的最新研究成果，该研究自然地推广了标准线性赌博机设置。主要结论是：单一算法——信息导向采样（IDS）在所有有限动作博弈中（几乎）实现了最坏情况下的最优率。我们提出了一个简洁且统一的随机部分监控分析方法，并进一步将该模型扩展到上下文及核化场景中。