(ensuring equity), incorporates queueing dynamics (to capture waiting time dynamics), and arm dependence (to capture learning …-based learning, fairness, queueing dynamics, and arm dependence: We prove that the regrets of all of our algorithms are bounded by O …-based learning, fairness, queueing, and arm dependence exist. From an application standpoint, our algorithms could be applied to help …

Traditional queuing theory assumes types are known or perfectly observed, and each type is typically put in its type …-specific queue which is prioritized using some version of the celebrated c-mu rule; we call this type-based queueing. We study … feature-based priority queuing where types are not perfectly observed but are inferred from observed features using a …