当前位置: X-MOL 学术arXiv.cs.IT › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Information Avoidance and Overvaluation in Sequential Decision Making under Epistemic Constraints
arXiv - CS - Information Theory Pub Date : 2021-06-09 , DOI: arxiv-2106.04984
Shuo Li, Matteo Pozzi

Decision makers involved in the management of civil assets and systems usually take actions under constraints imposed by societal regulations. Some of these constraints are related to epistemic quantities, as the probability of failure events and the corresponding risks. Sensors and inspectors can provide useful information supporting the control process (e.g. the maintenance process of an asset), and decisions about collecting this information should rely on an analysis of its cost and value. When societal regulations encode an economic perspective that is not aligned with that of the decision makers, the Value of Information (VoI) can be negative (i.e., information sometimes hurts), and almost irrelevant information can even have a significant value (either positive or negative), for agents acting under these epistemic constraints. We refer to these phenomena as Information Avoidance (IA) and Information OverValuation (IOV). In this paper, we illustrate how to assess VoI in sequential decision making under epistemic constraints (as those imposed by societal regulations), by modeling a Partially Observable Markov Decision Processes (POMDP) and evaluating non optimal policies via Finite State Controllers (FSCs). We focus on the value of collecting information at current time, and on that of collecting sequential information, we illustrate how these values are related and we discuss how IA and IOV can occur in those settings.

中文翻译:

认知约束下顺序决策中的信息回避和高估

参与民用资产和系统管理的决策者通常在社会法规的约束下采取行动。其中一些约束与认知量有关,如故障事件的概率和相应的风险。传感器和检查员可以提供支持控制过程(例如资产的维护过程)的有用信息,关于收集这些信息的决策应该依赖于对其成本和价值的分析。当社会法规对与决策者的观点不一致的经济观点进行编码时,信息价值 (VoI) 可能是负面的(即信息有时会受到伤害),几乎不相关的信息甚至可能具有重要价值(正面或负),对于在这些认知约束下行动的代理。我们将这些现象称为信息回避 (IA) 和信息高估 (IOV)。在本文中,我们通过对部分可观察马尔可夫决策过程 (POMDP) 建模并通过有限状态控制器 (FSC) 评估非最优策略,说明了如何在认知约束(如社会法规强加的约束)下评估顺序决策中的 VoI。我们专注于收集当前时间信息的价值,以及收集顺序信息的价值,我们说明了这些价值是如何相关的,我们讨论了 IA 和 IOV 如何在这些环境中发生。通过对部分可观察马尔可夫决策过程 (POMDP) 建模并通过有限状态控制器 (FSC) 评估非最优策略。我们专注于收集当前时间信息的价值,以及收集顺序信息的价值,我们说明了这些价值是如何相关的,我们讨论了 IA 和 IOV 如何在这些环境中发生。通过对部分可观察马尔可夫决策过程 (POMDP) 建模并通过有限状态控制器 (FSC) 评估非最优策略。我们专注于收集当前时间信息的价值,以及收集顺序信息的价值,我们说明了这些价值是如何相关的,我们讨论了 IA 和 IOV 如何在这些环境中发生。
更新日期:2021-06-10
down
wechat
bug