Algorithmic Hysteresis: Structural Failure of Decision-Making Under Irreversible Latency

Fuente: Zenodo
Guardado en:
Detalles Bibliográficos
Autor principal: Tavella, Danilo
Formato: Recurso digital
Lenguaje:inglés
Publicado: Zenodo 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866901606224625664
author Tavella, Danilo
author_facet Tavella, Danilo
contents <div>Decision-making under irreversible costs and delayed information poses a structural challenge to adaptive systems. While it is commonly assumed that the availability of reliable data eventually corrects suboptimal behavior, work under irreversible latency shows that such adaptation is not guaranteed and depends critically on the internal structure of the decision process.</div> <div> </div> <div>This technical note introduces a minimal decision environment with irreversible penalties and delayed noisy signals, and identifies three distinct dynamical regimes across standard reinforcement learning paradigms. Off-policy value-based methods exhibit algorithmic hysteresis, forming irreversible commitments prior to information availability. On-policy value-based methods preserve uncertainty but fail to convert information into structure, resulting in epistemic inertia. Policy-based methods display signal-driven adaptation, reorganizing behavior upon the arrival of informative signals.</div> <div> </div> <div>The results establish a structural trilemma for adaptive decision-making under irreversibility and reveal that failure modes arise independently of parameter tuning or optimization quality. The contribution is diagnostic rather than prescriptive, identifying limits beyond which standard decision mechanisms cannot sustain meaningful adaptive temporal structure.</div> <p> </p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18184182
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Algorithmic Hysteresis: Structural Failure of Decision-Making Under Irreversible Latency
Tavella, Danilo
algorithmic hysteresis
irreversibility
decision-making
reinforcement learning
delayed information
structural failure
clockability
<div>Decision-making under irreversible costs and delayed information poses a structural challenge to adaptive systems. While it is commonly assumed that the availability of reliable data eventually corrects suboptimal behavior, work under irreversible latency shows that such adaptation is not guaranteed and depends critically on the internal structure of the decision process.</div> <div> </div> <div>This technical note introduces a minimal decision environment with irreversible penalties and delayed noisy signals, and identifies three distinct dynamical regimes across standard reinforcement learning paradigms. Off-policy value-based methods exhibit algorithmic hysteresis, forming irreversible commitments prior to information availability. On-policy value-based methods preserve uncertainty but fail to convert information into structure, resulting in epistemic inertia. Policy-based methods display signal-driven adaptation, reorganizing behavior upon the arrival of informative signals.</div> <div> </div> <div>The results establish a structural trilemma for adaptive decision-making under irreversibility and reveal that failure modes arise independently of parameter tuning or optimization quality. The contribution is diagnostic rather than prescriptive, identifying limits beyond which standard decision mechanisms cannot sustain meaningful adaptive temporal structure.</div> <p> </p>
title Algorithmic Hysteresis: Structural Failure of Decision-Making Under Irreversible Latency
topic algorithmic hysteresis
irreversibility
decision-making
reinforcement learning
delayed information
structural failure
clockability
url https://doi.org/10.5281/zenodo.18184182