序列上的决策:可计算性与选择
Decisions over Sequences: Computability and Choice
AI总结:
该研究开发了序列决策框架,确立了停止规则与有界停止规则的等价性,证明可计算规则可由有限自动机实现,扩展了抽象选择理论至无限序列,并刻画了两类选择程序。
摘要:
我们开发了一个框架,用于研究决策者依次面临备选方案的情形。在该框架内,我们关注内生停止行为,采用两类广泛的决策规则:\textit{停止规则}与\textit{有界停止规则}。我们确立了这两类规则的等价性,并考察其两项含义:其一,聚焦决策的程序层面,我们利用图灵机模型定义\textit{可计算}规则,等价性结果使我们能证明可计算规则可由有限自动机实现;其二,我们将抽象选择理论的设定从集合与有限列表上的选择,扩展至\textit{备选方案的无限序列}上的选择,等价性结果使我们能推导选择行为的\textit{可检验含义}。我们开发了一个显示偏好“工具包”,并用以刻画基于阈值的选择程序与满意型选择程序。
英文摘要:
We develop a framework to study situations where decision makers face alternatives sequentially. Within this framework, we focus on endogenous stopping behavior using two broad classes of decision rules: \textit{stopping rules} and \textit{bounded stopping rules}. We establish the equivalence of these two classes and examine two of its implications. First, focusing on the procedural aspects of decision making, we define \textit{computable} rules using the model of a Turing machine. Our equivalence result enables us to show that computable rules are implementable by finite automata. Second, we extend the setup of abstract choice theory beyond choice from sets and finite lists, to that from \textit{infinite sequences} of alternatives. The equivalence result allows us to derive \textit{testable implications} of choice behavior. We develop a revealed-preference ``toolkit'' and use it to characterize a threshold-based and a satisficing choice procedure.
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。