Normative rule extraction from implicit learning into explicit representation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F20%3A50017203" target="_blank" >RIV/62690094:18450/20:50017203 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.3233/FAIA200555" target="_blank" >http://dx.doi.org/10.3233/FAIA200555</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3233/FAIA200555" target="_blank" >10.3233/FAIA200555</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Normative rule extraction from implicit learning into explicit representation

Popis výsledku v původním jazyce

Normative multi-agent research is an alternative viewpoint in the design of adaptive autonomous agent architecture. Norms specify the standards of behaviors such as which actions or states should be achieved or avoided. The concept of norm synthesis is the process of generating useful normative rules. This study proposes a model for normative rule extraction from implicit learning, namely using the Q-learning algorithm, into explicit norm representation by implementing Dynamic Deontics and Hierarchical Knowledge Base (HKB) to synthesize useful normative rules in the form of weighted state-action pairs with deontic modality. OpenAi Gym is used to simulate the agent environment. Our proposed model is able to generate both obligative and prohibitive norms as well as deliberate and execute said norms. Results show the generated norms are best used as prior knowledge to guide agent behavior and performs poorly if not complemented by another agent coordination mechanism. Performance increases when using both obligation and prohibition norms, and in general, norms do speed up optimum policy reachability. © 2020 The authors and IOS Press. All rights reserved.

Název v anglickém jazyce

Normative rule extraction from implicit learning into explicit representation

Popis výsledku anglicky

Normative multi-agent research is an alternative viewpoint in the design of adaptive autonomous agent architecture. Norms specify the standards of behaviors such as which actions or states should be achieved or avoided. The concept of norm synthesis is the process of generating useful normative rules. This study proposes a model for normative rule extraction from implicit learning, namely using the Q-learning algorithm, into explicit norm representation by implementing Dynamic Deontics and Hierarchical Knowledge Base (HKB) to synthesize useful normative rules in the form of weighted state-action pairs with deontic modality. OpenAi Gym is used to simulate the agent environment. Our proposed model is able to generate both obligative and prohibitive norms as well as deliberate and execute said norms. Results show the generated norms are best used as prior knowledge to guide agent behavior and performs poorly if not complemented by another agent coordination mechanism. Performance increases when using both obligation and prohibition norms, and in general, norms do speed up optimum policy reachability. © 2020 The authors and IOS Press. All rights reserved.

Druh

D - Stať ve sborníku

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

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

Frontiers in Artificial Intelligence and Applications

ISBN

978-1-64368-114-6

ISSN

0922-6389

e-ISSN

—

Počet stran výsledku

14

Strana od-do

88-101

Název nakladatele

IOS Press BV

Místo vydání

Amsterdam

Místo konání akce

Japonsko

Datum konání akce

22. 10. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—