量化感知、预测等能力对决策的价值，揭示其协同作用机制
One if by Land, Two if by Sea, Three if by Four Seas, and More to Come -- Values of Perception, Prediction, Communication, and Common Sense in Decision Making
- 从决策理论出发定义感知、预测等信息价值的数学量
- 发现仅靠感知可能降低决策效果，需与预测结合才有效
- 适用于自动驾驶系统设计，也启发对人类决策机制的理解
本文旨在严格定义感知、预测、通信和常识在决策中的价值。这些量基于决策理论，但具有信息论类比关系，具备与香农熵和互信息相似的基本数学性质，在特定条件下可退化为这些量。一个关键发现是：仅有感知而无预测时，其价值可能为负；而感知加预测或仅预测的价值始终非负。这些定义有助于回答自主决策系统设计中的实际问题，例如：是否需要观测并预测某智能体的行为？重要性如何？应按何种顺序观测与预测各智能体？该框架还可能为认知科学与神经科学提供洞见，帮助理解自然决策者如何利用来自不同来源与操作的信息。
原文摘要 · Abstract (English)
This work aims to rigorously define the values of perception, prediction, communication, and common sense in decision making. The defined quantities are decision-theoretic, but have information-theoretic analogues, e.g., they share some simple but key mathematical properties with Shannon entropy and mutual information, and can reduce to these quantities in particular settings. One interesting observation is that, the value of perception without prediction can be negative, while the value of perception together with prediction and the value of prediction alone are always nonnegative. The defined quantities suggest answers to practical questions arising in the design of autonomous decision-making systems. Example questions include: Do we need to observe and predict the behavior of a particular agent? How important is it? What is the best order to observe and predict the agents? The defined quantities may also provide insights to cognitive science and neural science, toward the understanding of how natural decision makers make use of information gained from different sources and operations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。