Decision Theory without Logical Omniscience: Toward an Axiomatic Framework for Bounded Rationality
提出将有限理性代理人建模为非逻辑全知者，即他们不知道自己所知的所有逻辑或数学推论。在极弱条件下，从代理人偏好中推导出主观状态空间，并得到主观期望效用表示，旨在使该有限理性模型更易于应用。
I propose modelling boundedly rational agents as agents who are not logically omniscient—that is, who do not know all logical or mathematical implications of what they know. I show how a subjective state space can be derived as part of a subjective expected utility representation of the agent's preferences. The representation exists under very weak conditions. The representation uses the familiar language of probability, utility, and states of the world in the hope that this makes this model of bounded rationality easier to use in applications.