Norm Augmented Reinforcement Learning Agents With Synthesized Normative Rules: A Proposed Normative Agent Framework

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F24%3A50021597" target="_blank" >RIV/62690094:18450/24:50021597 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.igi-global.com/gateway/article/345650" target="_blank" >https://www.igi-global.com/gateway/article/345650</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.4018/JCIT.345650" target="_blank" >10.4018/JCIT.345650</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Norm Augmented Reinforcement Learning Agents With Synthesized Normative Rules: A Proposed Normative Agent Framework

Popis výsledku v původním jazyce

The dynamic deontic (DD) is a norm synthesis framework that extracts normative rules from reinforcement learning (RL), however it was not designed to be applied in agent coordination. This study proposes a norm augmented reinforcement learning framework (NARLF) that extends said model to include a norm deliberation mechanism for learned norms re-imputation for norm biased decision-making RL agents. This study aims to test the effects of synthesized norms applied on-line and off-line on agent learning performance. The framework consists of the DD framework extended with a pre-processing and deliberation component to allow re-imputation of normative rules. A deliberation model, the Norm Augmented Q-Table (NAugQT), is proposed to map normative rules into RL agents via q-values weight updates. Results show that the framework is able to map and improve RL agent’s performance but only when synthesized off-line edited absolute norm salience value norms are used. This shows limitations when unstable salience norms are applied. Improvement in norm extraction and pre-processing are required. © 2024 IGI Global. All rights reserved.

Název v anglickém jazyce

Norm Augmented Reinforcement Learning Agents With Synthesized Normative Rules: A Proposed Normative Agent Framework

Popis výsledku anglicky

The dynamic deontic (DD) is a norm synthesis framework that extracts normative rules from reinforcement learning (RL), however it was not designed to be applied in agent coordination. This study proposes a norm augmented reinforcement learning framework (NARLF) that extends said model to include a norm deliberation mechanism for learned norms re-imputation for norm biased decision-making RL agents. This study aims to test the effects of synthesized norms applied on-line and off-line on agent learning performance. The framework consists of the DD framework extended with a pre-processing and deliberation component to allow re-imputation of normative rules. A deliberation model, the Norm Augmented Q-Table (NAugQT), is proposed to map normative rules into RL agents via q-values weight updates. Results show that the framework is able to map and improve RL agent’s performance but only when synthesized off-line edited absolute norm salience value norms are used. This shows limitations when unstable salience norms are applied. Improvement in norm extraction and pre-processing are required. © 2024 IGI Global. All rights reserved.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název periodika

Journal of Cases on Information Technology

ISSN

1548-7717

e-ISSN

1548-7725

Svazek periodika

26

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

34

Strana od-do

1-34

Kód UT WoS článku

001283032700001

EID výsledku v databázi Scopus

2-s2.0-85199374981