未观测到代理奖励和完全知识代理的重复委托代理博弈【英文版】

英文标题：Repeated Principal-Agent Games with Unobserved Agent Rewards and Perfect-Knowledge Agents中文摘要：本研究在多臂赌博 (MAB) 框架下研究重复的主体 - 代理博弈场景，在代理人具有完美知识的情况下，构建了一个估计代理人期望奖励的估计器，并设计了一个低遗憾策略，为主体策略提供了指导，同时在协作交通规划等领域具有一定的应用前景。英文摘要：Motivated by a number of real-world applications from domains like healthcareand sustainable transportation, in this paper we study a scenario of repeatedprincipal-agent games within a multi-armed bandit (MAB) framework, where: theprincipal gives a different incentive for each ban