Skip to content
DraconiticResearch
Search Sources API
203,948 studies31 sourcesUpdated 19 min ago
PreprintarXiv licencearXiv

Value of Information in Dynamic Decision Making

  • Dimitry Shaiderman
  • Eilon Solan
Open at sourcePDFDOICite

Abstract

We study the value of information in predicting the evolving state of a finite Markov chain. At each stage, a decision maker chooses a state and observes only whether the current state of the chain matches her choice; the resulting information is used to make a prediction on the state at the final stage of the problem. We show that, when the chain starts from an invariant distribution, the optimal terminal value is non-decreasing with the number of observations and converges at a uniform exponential rate. We introduce the predictive learning index, which measures whether all attainable informational value is extracted after finitely many observations, and show that both finite and infinite indices may occur. In contrast, for nonstationary initial distributions, the value may strictly decrease with the horizon.

Related

  1. Dynamic Programming for Value-at-Risk Markov Decision Processes in Continuous Spaces
    Xian Chen, Erick Delage, Weikai Wang
    arXivPreprintCC BY-NC-ND 4.0Full textOptimisation & controlarXiv
  2. Evaluation of Panel and Site Selection for a Solar Power Plant Using Geographic Information Systems and an Integrated Multi-Criteria Decision-Making Framework
    Katre Akay, Yaren Doğan, Bengisu Topcu +5
    MathematicsPeer-reviewedCC BY 4.0Full textGeneral mathematicsCrossrefDOAJ
  3. Ex Ante and Scenario-Conditional Value of Information in Dynamic Portfolio Choice
    Tom Pohlschmidt, Shihao Zhu
    arXivPreprintCC BY 4.0Full textOptimisation & controlarXiv
  4. Classes of Aggregation Rules for Ethical Decision Making in Automated Systems
    Federico Fioravanti, Iyad Rahwan, Fernando Tohmé
    HALPreprintLicence not statedGeneral mathematicsHAL
  5. Risk-Averse Decision Making with Multi-Level Reliability Guarantees
    Amirmohammad Farzaneh, Osvaldo Simeone
    arXivPreprintCC BY 4.0Full textStatisticsarXiv

Cite

BibTeXRIS
BibTeX
@misc{shaiderman2026value,
  title = {{Value of Information in Dynamic Decision Making}},
  author = {Dimitry Shaiderman and Eilon Solan},
  howpublished = {arXiv},
  year = {2026},
  month = aug,
  doi = {10.48550/arxiv.2608.29273},
  eprint = {2608.29273},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.29273},
}
RIS
TY  - UNPB
TI  - Value of Information in Dynamic Decision Making
AU  - Dimitry Shaiderman
AU  - Eilon Solan
PY  - 2026
DA  - 2026/08/29
PB  - arXiv
DO  - 10.48550/arxiv.2608.29273
UR  - https://arxiv.org/abs/2608.29273
AB  - We study the value of information in predicting the evolving state of a finite Markov chain. At each stage, a decision maker chooses a state and observes only whether the current state of the chain matches her choice; the resulting information is used to make a prediction on the state at the final stage of the problem. We show that, when the chain starts from an invariant distribution, the optimal terminal value is non-decreasing with the number of observations and converges at a uniform exponential rate. We introduce the predictive learning index, which measures whether all attainable informational value is extracted after finitely many observations, and show that both finite and infinite indices may occur. In contrast, for nonstationary initial distributions, the value may strictly decrease with the horizon.
ER  -