A growing body of work in economics and computation focuses on the trade-off between implementability and simplicity in mechanism design. The goal is to develop a theory that not only allows to design an incentive structure easy to grasp for imperfectly rational agents, but also understand the ensuing limitations on the class of mechanisms that enforce it. In this context, the concept of OSP mechanisms has assumed a prominent role since they provably account for the absence of contingent reasoning skills, a specific cognitive limitation. For single-dimensional agents, it is known that OSP mechanisms need to use certain greedy algorithms. In this work, we introduce a notion that interpolates between OSP and SOSP, a more stringent notion where agents only plan a subset of their own future moves. We provide an algorithmic characterization of this novel class of mechanisms for single-dimensional domains and binary allocation problems, that precisely measures the interplay between simplicity and implementability. We build on this to show how mechanisms based on reverse greedy algorithms (a.k.a., deferred acceptance auctions) are algorithmically more robust to imperfectly rationality than those adopting greedy algorithms.

翻译：经济学与计算领域日益关注机制设计中可实施性与简单性之间的权衡。其目标不仅是设计一种易于被非完全理性智能体理解的激励结构，更要厘清其强制执行所依赖的机制类别受到的约束。在此背景下，OSP机制的概念占据重要地位，因其被证明确实解释了缺乏权变推理能力这一特定认知局限。对于单维智能体，已知OSP机制需采用特定贪心算法。本文引入一个介于OSP与SOSP（一种更严格的概念，要求智能体仅规划自身未来部分行动）之间的概念。针对单维域和二元分配问题，我们给出这类新型机制的算法刻画，精确衡量简单性与可实施性之间的相互作用。基于此，我们证明基于反向贪心算法（即延迟接受拍卖）的机制在算法上比采用贪心算法的机制对非完全理性具有更强的鲁棒性。