Information Avoidance and Overvaluation in Sequential Decision Making
under Epistemic Constraints
- URL: http://arxiv.org/abs/2106.04984v1
- Date: Wed, 9 Jun 2021 11:05:13 GMT
- Title: Information Avoidance and Overvaluation in Sequential Decision Making
under Epistemic Constraints
- Authors: Shuo Li, Matteo Pozzi
- Abstract summary: Decision makers involved in the management of civil assets and systems 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.
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.
We refer to these phenomena as Information Avoidance (IA) and Information OverValuation (IOV)
- Score: 6.0288766970390455
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: 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.
Related papers
- Language Models Can Reduce Asymmetry in Information Markets [100.38786498942702]
We introduce an open-source simulated digital marketplace where intelligent agents, powered by language models, buy and sell information on behalf of external participants.
The central mechanism enabling this marketplace is the agents' dual capabilities: they have the capacity to assess the quality of privileged information but also come equipped with the ability to forget.
To perform well, agents must make rational decisions, strategically explore the marketplace through generated sub-queries, and synthesize answers from purchased information.
arXiv Detail & Related papers (2024-03-21T14:48:37Z) - QuantTM: Business-Centric Threat Quantification for Risk Management and Cyber Resilience [0.259990372084357]
QuantTM is an approach that incorporates views from operational and strategic business representatives to collect threat information.
It empowers the analysis of threats' impacts and the applicability of security controls.
arXiv Detail & Related papers (2024-02-21T21:34:06Z) - Accountability in Offline Reinforcement Learning: Explaining Decisions
with a Corpus of Examples [70.84093873437425]
This paper introduces the Accountable Offline Controller (AOC) that employs the offline dataset as the Decision Corpus.
AOC operates effectively in low-data scenarios, can be extended to the strictly offline imitation setting, and displays qualities of both conservation and adaptability.
We assess AOC's performance in both simulated and real-world healthcare scenarios, emphasizing its capability to manage offline control tasks with high levels of performance while maintaining accountability.
arXiv Detail & Related papers (2023-10-11T17:20:32Z) - Towards a multi-stakeholder value-based assessment framework for
algorithmic systems [76.79703106646967]
We develop a value-based assessment framework that visualizes closeness and tensions between values.
We give guidelines on how to operationalize them, while opening up the evaluation and deliberation process to a wide range of stakeholders.
arXiv Detail & Related papers (2022-05-09T19:28:32Z) - Inverse Online Learning: Understanding Non-Stationary and Reactionary
Policies [79.60322329952453]
We show how to develop interpretable representations of how agents make decisions.
By understanding the decision-making processes underlying a set of observed trajectories, we cast the policy inference problem as the inverse to this online learning problem.
We introduce a practical algorithm for retrospectively estimating such perceived effects, alongside the process through which agents update them.
Through application to the analysis of UNOS organ donation acceptance decisions, we demonstrate that our approach can bring valuable insights into the factors that govern decision processes and how they change over time.
arXiv Detail & Related papers (2022-03-14T17:40:42Z) - Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in
Partially Observed Markov Decision Processes [65.91730154730905]
In applications of offline reinforcement learning to observational data, such as in healthcare or education, a general concern is that observed actions might be affected by unobserved factors.
Here we tackle this by considering off-policy evaluation in a partially observed Markov decision process (POMDP)
We extend the framework of proximal causal inference to our POMDP setting, providing a variety of settings where identification is made possible.
arXiv Detail & Related papers (2021-10-28T17:46:14Z) - Reviving Purpose Limitation and Data Minimisation in Personalisation,
Profiling and Decision-Making Systems [0.0]
This paper determines, through an interdisciplinary law and computer science lens, whether data minimisation and purpose limitation can be meaningfully implemented in data-driven systems.
Our analysis reveals that the two legal principles continue to play an important role in mitigating the risks of personal data processing.
We highlight that even though these principles are important safeguards in the systems under consideration, there are important limits to their practical implementation.
arXiv Detail & Related papers (2021-01-15T16:36:29Z) - Inverse Active Sensing: Modeling and Understanding Timely
Decision-Making [111.07204912245841]
We develop a framework for the general setting of evidence-based decision-making under endogenous, context-dependent time pressure.
We demonstrate how it enables modeling intuitive notions of surprise, suspense, and optimality in decision strategies.
arXiv Detail & Related papers (2020-06-25T02:30:45Z) - Learning Robust Decision Policies from Observational Data [21.05564340986074]
It is of interest to learn robust policies that reduce the risk of outcomes with high costs.
We develop a method for learning policies that reduce tails of the cost distribution at a specified level.
arXiv Detail & Related papers (2020-06-03T16:02:57Z) - Value of structural health information in partially observable
stochastic environments [0.0]
We introduce and study the theoretical and computational foundations of the Value of Information (VoI) and the Value of Structural Health Monitoring (VoSHM)
It is shown that a POMDP policy inherently leverages the notion of VoI to guide observational actions in an optimal way at every decision step.
arXiv Detail & Related papers (2019-12-28T22:18:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.