Learning of Autonomous Agent in Virtual Environment

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F12%3A00195397" target="_blank" >RIV/68407700:21230/12:00195397 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.scs-europe.net/conf/ecms2012/ecms2012%20accepted%20papers/is_ECMS_0084.pdf" target="_blank" >http://www.scs-europe.net/conf/ecms2012/ecms2012%20accepted%20papers/is_ECMS_0084.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Learning of Autonomous Agent in Virtual Environment

Popis výsledku v původním jazyce

Presented topic is from area of development of artificial creatures and proposes new architecture of autonomous agent. This architecture design combines knowledge from Artificial Intelligence (AI), Ethology, Artificial Life and Intelligent Robotics. Fromthe field of classical AI, the fusion of Reinforcement Learning (RL), planning and artificial neural network into one more complex control system was used here. The main principle of its function is inspired by the field of Ethology, this means that life of given agent tries to be similar to life of an animal in the Nature, where animal learns relatively autonomously from simpler principles towards the more complex ones. The architecture supports on-line learning of all knowledge from the scratch, while the core principle is in hierarchical (RL); this action hierarchy is created autonomously based solely on agent's interaction with an environment. The key idea is in original implementation of a domain independent hierarchical planner.

Název v anglickém jazyce

Learning of Autonomous Agent in Virtual Environment

Popis výsledku anglicky

Presented topic is from area of development of artificial creatures and proposes new architecture of autonomous agent. This architecture design combines knowledge from Artificial Intelligence (AI), Ethology, Artificial Life and Intelligent Robotics. Fromthe field of classical AI, the fusion of Reinforcement Learning (RL), planning and artificial neural network into one more complex control system was used here. The main principle of its function is inspired by the field of Ethology, this means that life of given agent tries to be similar to life of an animal in the Nature, where animal learns relatively autonomously from simpler principles towards the more complex ones. The architecture supports on-line learning of all knowledge from the scratch, while the core principle is in hierarchical (RL); this action hierarchy is created autonomously based solely on agent's interaction with an environment. The key idea is in original implementation of a domain independent hierarchical planner.

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

<a href="/cs/project/1M0567" target="_blank" >1M0567: Centrum aplikované kybernetiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2012

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings 26th European Conference on Modelling and Simulation ECMS 2012

ISBN

978-0-9564944-4-3

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

373-379

Název nakladatele

European Council for Modelling and Simulation

Místo vydání

Brusel

Místo konání akce

Koblenz

Datum konání akce

29. 5. 2012

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—