Fair Contextual Multi-Armed Bandits: Theory and Experiments
Fair Contextual Multi-Armed Bandits: Theory and Experiments
复制标题
DOI：
--
复制
发表时间：
2019-12
期刊：
影响因子：
--
通讯作者：
Yifang Chen;Alex Cuellar;Haipeng Luo;Jignesh Modi;Heramb Nemlekar;S. Nikolaidis
中科院分区：
文献类型：
--
作者：
Yifang Chen;Alex Cuellar;Haipeng Luo;Jignesh Modi;Heramb Nemlekar;S. Nikolaidis
当AI系统与多个用户交互时，它经常需要做出分配决策。例如，虚拟代理决定在组设置中关注谁，或者工厂机器人选择工人来交付零件。在决策过程中表现出公平性对于这类系统被广泛接受至关重要。我们引入了一个多臂强盗算法的公平性约束，其中公平性被定义为一个任务或资源分配给一个用户的最小速率。该算法使用上下文信息的用户和任务，并没有假设如何捕捉不同用户的性能损失产生。我们提供了理论保证的性能和实证结果模拟和在线用户研究。结果强调了在公平决策中考虑上下文的好处，特别是当用户在某些上下文中表现更好而在其他上下文中表现更差时。
When an AI system interacts with multiple users, it frequently needs to make allocation decisions. For instance, a virtual agent decides whom to pay attention to in a group setting, or a factory robot selects a worker to deliver a part. Demonstrating fairness in decision making is essential for such systems to be broadly accepted. We introduce a Multi-Armed Bandit algorithm with fairness constraints, where fairness is defined as a minimum rate that a task or a resource is assigned to a user. The proposed algorithm uses contextual information about the users and the task and makes no assumptions on how the losses capturing the performance of different users are generated. We provide theoretical guarantees of performance and empirical results from simulation and an online user study. The results highlight the benefit of accounting for contexts in fair decision making, especially when users perform better at some contexts and worse at others.