Adaptive Agents for Artificial Life Domain

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F04%3A00101770" target="_blank" >RIV/68407700:21230/04:00101770 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Adaptive Agents for Artificial Life Domain

Original language description

Adaptation and real time behavior becomes a necessity for agents that want to survive in Artificial Life environments. The neurodynamic reinforcement learning approach - Q-learning where Q-factors are represented using neural networks, overcomes problemsof the classical unsupervised algorithms. This research that is mainly focused on design of agent architectures for Artificial Life introduces the concepts of parallel and dynamic Q-spaces, where the learned Q-factors are divided into separate action-state spaces that correspond to independent behaviors. Q-factors are then combined across these spaces based on relationship among higher-level behaviors. A simulated Artificial Life environment with Artificial Life agents has been used as a test bed. Theresearch is being conducted in the Artificial Life domain. The proposed techniques will be useful in different domains also.

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

JC - Computer hardware and software

OECD FORD branch

—

Project

—

Continuities

V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Publication year

2004

Confidentiality

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

Name of the periodical

WSEAS Transactions on Systems

ISSN

1109-2777

e-ISSN

—

Volume of the periodical

6

Issue of the periodical within the volume

3

Country of publishing house

GR - GREECE

Number of pages

6

Pages from-to

—

UT code for WoS article

—

EID of the result in the Scopus database

—