A systematic review of human-centered explainability in reinforcement learning. Transferring the RCC framework to support epistemic trustworthiness

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985955%3A_____%2F25%3A00639875" target="_blank" >RIV/67985955:_____/25:00639875 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/s42454-025-00084-w" target="_blank" >https://doi.org/10.1007/s42454-025-00084-w</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s42454-025-00084-w" target="_blank" >10.1007/s42454-025-00084-w</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A systematic review of human-centered explainability in reinforcement learning. Transferring the RCC framework to support epistemic trustworthiness

Popis výsledku v původním jazyce

This paper presents a systematic review of explainable reinforcement learning methodologies with an emphasis on human-centered evaluation frameworks. Drawing from literature between 2017 and 2025, we apply and extend the Reasons, Confidence, and Counterfactuals (RCC) Framework – originally designed for supervised learning – to reinforcement learning contexts. Our analysis reveals two predominant explanatory strategies: constructive, where explicit explanations are generated, and supportive, where users must infer reasoning from provided visual or textual cues. Our review also emphasizes human factor considerations, like task complexity, explanation formats, and evaluation methodologies. Particularly, for the latter, our analysis shows that improvement of the quality of decision is rarely measured.

Název v anglickém jazyce

A systematic review of human-centered explainability in reinforcement learning. Transferring the RCC framework to support epistemic trustworthiness

Popis výsledku anglicky

This paper presents a systematic review of explainable reinforcement learning methodologies with an emphasis on human-centered evaluation frameworks. Drawing from literature between 2017 and 2025, we apply and extend the Reasons, Confidence, and Counterfactuals (RCC) Framework – originally designed for supervised learning – to reinforcement learning contexts. Our analysis reveals two predominant explanatory strategies: constructive, where explicit explanations are generated, and supportive, where users must infer reasoning from provided visual or textual cues. Our review also emphasizes human factor considerations, like task complexity, explanation formats, and evaluation methodologies. Particularly, for the latter, our analysis shows that improvement of the quality of decision is rarely measured.

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

60301 - Philosophy, History and Philosophy of science and technology

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Human-Intelligent Systems Integration

ISSN

2524-4876

e-ISSN

2524-4884

Svazek periodika

7

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

10

Strana od-do

239-248

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—