一种具有自治Agent的可操纵的真实利润最大化机制设计
A Tractable Truthful Profit Maximization Mechanism Design with Autonomous Agents
摘要：
任务分配是现代系统中的一个关键过程，但它经常受到有关参与代理效用的不完全信息的挑战。在本文中，我们提出了一个新的利润最大化机制的任务分配问题，任务发布者寻求一个最佳的激励函数，以最大限度地提高自己的利润，同时确保代理的私人信息（类型）的真实宣布，并在任务中的参与，而自主代理的目标是最大限度地提高自己的效用函数，通过决定其参与水平和宣布类型。我们的机制从基于经典契约理论的真实机制中脱颖而出，因为它使代理能够自己决定他们的参与程度，使其对许多现实世界的任务分配场景更加实用。事实证明，通过考虑由任务发布者的两个决策函数组成的线性形式的激励函数，该机制的目标就得到了满足。建议的真实机制最初建模为一个非凸函数优化的双重连续的约束，然而，我们证明，通过推导出一个等价形式的激励约束，它可以重新表述为一个易于处理的凸最优控制问题。此外，我们提出了一个数值算法来获得解决方案。
英文摘要：
Task allocation is a crucial process in modern systems, but it is often challenged by incomplete information about the utilities of participating agents. In this paper, we propose a new profit maximization mechanism for the task allocation problem, where the task publisher seeks an optimal incentive function to maximize its own profit and simultaneously ensure the truthful announcing of the agent's private information (type) and its participation in the task, while an autonomous agent aims at maximizing its own utility function by deciding on its participation level and announced type. Our mechanism stands out from the classical contract theory-based truthful mechanisms as it empowers agents to make their own decisions about their level of involvement, making it more practical for many real-world task allocation scenarios. It has been proven that by considering a linear form of incentive function consisting of two decision functions for the task publisher the mechanism's goals are met. The proposed truthful mechanism is initially modeled as a non-convex functional optimization with the double continuum of constraints, nevertheless, we demonstrate that by deriving an equivalent form of the incentive constraints, it can be reformulated as a tractable convex optimal control problem. Further, we propose a numerical algorithm to obtain the solution.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
