具有持续改进能力的智能体下的算法决策
Algorithmic Decision-Making under Agents with Persistent Improvement
AI总结:
本文针对人类策略行为下的算法决策问题,构建动态模型与Stackelberg博弈刻画努力的持续改进效应,推导均衡与激励条件,并扩展模型分析不诚实行为与遗忘性努力的影响,为决策者设计最优激励策略提供理论支撑。
摘要:
本文研究人类策略行为下的算法决策问题:决策者使用算法对人类智能体做出决策,而了解算法信息的智能体会策略性地付出努力并提升自身,以获得有利决策。现有研究假设智能体可立即从其努力中获益,与之不同,我们考虑更现实的场景:努力的影响具有持续性,智能体通过逐步提升从努力中获益。我们首先构建了一个动态模型来刻画持续改进过程,并在此基础上建立Stackelberg博弈以建模智能体与决策者之间的互动。我们解析刻画了均衡策略,并明确了智能体有改进动机的条件。基于该动态特性,我们进一步研究决策者如何设计最优策略,以激励智能体群体实现最大程度的改进。我们还将模型扩展到两类场景:1)智能体可能不诚实,利用算法漏洞获得有利但错误的决策;2)诚实的努力具有遗忘性,不足以保证持续改进。通过扩展模型,我们进一步探究了智能体更偏好诚实努力而非不诚实行为的条件,以及遗忘性努力带来的影响。
英文摘要:
This paper studies algorithmic decision-making under human's strategic behavior, where a decision maker uses an algorithm to make decisions about human agents, and the latter with information about the algorithm may exert effort strategically and improve to receive favorable decisions. Unlike prior works that assume agents benefit from their efforts immediately, we consider realistic scenarios where the impacts of these efforts are persistent and agents benefit from efforts by making improvements gradually. We first develop a dynamic model to characterize persistent improvements and based on this construct a Stackelberg game to model the interplay between agents and the decision-maker. We analytically characterize the equilibrium strategies and identify conditions under which agents have incentives to improve. With the dynamics, we then study how the decision-maker can design an optimal policy to incentivize the largest improvements inside the agent population. We also extend the model to settings where 1) agents may be dishonest and game the algorithm into making favorable but erroneous decisions; 2) honest efforts are forgettable and not sufficient to guarantee persistent improvements. With the extended models, we further examine conditions under which agents prefer honest efforts over dishonest behavior and the impacts of forgettable efforts.
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。