Reusable Reinforcement Learning for Modular Self Motivated Agents

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00218087" target="_blank" >RIV/68407700:21230/14:00218087 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.7148/2014-0352" target="_blank" >http://dx.doi.org/10.7148/2014-0352</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.7148/2014-0352" target="_blank" >10.7148/2014-0352</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Reusable Reinforcement Learning for Modular Self Motivated Agents

Popis výsledku v původním jazyce

Presented topic is from the research fields called Artificial Life and Artificial Intelligence (AI). In this paper, there is presented novel approach to designing agent architectures with its requiements. The approach in inspired by inherited modularityof biological brains and agent architectures are represented here as set of given reusable modules connected into a particular topology. This paper presents design of two particular modules for future use in more complex architectures. The modules are used for implementing model-free motivation-driven Reinforcement Learning (RL). First, the novel framework for these architectures is described together with a used simulator. Then, the design of two new reusable domain-independent components of agent architectures is described. Finally, expwerimental validation of these new components and their future use is mentioned.

Název v anglickém jazyce

Reusable Reinforcement Learning for Modular Self Motivated Agents

Popis výsledku anglicky

Presented topic is from the research fields called Artificial Life and Artificial Intelligence (AI). In this paper, there is presented novel approach to designing agent architectures with its requiements. The approach in inspired by inherited modularityof biological brains and agent architectures are represented here as set of given reusable modules connected into a particular topology. This paper presents design of two particular modules for future use in more complex architectures. The modules are used for implementing model-free motivation-driven Reinforcement Learning (RL). First, the novel framework for these architectures is described together with a used simulator. Then, the design of two new reusable domain-independent components of agent architectures is described. Finally, expwerimental validation of these new components and their future use is mentioned.

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2014

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of 28th European Conference on Modeling and Simulation

ISBN

978-0-9564944-8-1

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

352-358

Název nakladatele

European Council for Modelling and Simulation

Místo vydání

Brusel

Místo konání akce

Brescia

Datum konání akce

27. 5. 2014

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—