Ethological Concepts in Hierarchical Reinforcement Learning and Control of Intelligent Agents

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F09%3A00165338" target="_blank" >RIV/68407700:21230/09:00165338 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Ethological Concepts in Hierarchical Reinforcement Learning and Control of Intelligent Agents
Original language description
This paper integrates rigorous methods of reinforcement learning (RL) and control engineering with a behavioural (ethology) approach to the agent technology. The main outcome is a hybrid architecture for intelligent autonomous agents targeted to the Artificial Life like environments. The architecture adopts several biology concepts and shows that they can provide robust solutions to some areas. The resulting agents exhibit a wide range of behaviour from a simple primitive targeted behaviour to complex planning. The agent is fully autonomous through the environment feedback, evaluating internal agent state. This feedback motivates the agent to perform behaviours that return the agent towards optimal conditions
Czech name
—
Czech description
—

Project
<a href="/en/project/1M0567" target="_blank" >1M0567: Centre for Applied Cybernetics</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2009
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
23rd European Conference on Modelling and Simulation
ISBN
978-0-9553018-8-9
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
—
Publisher name
IEEE
Place of publication
Piscataway
Event location
Madrid
Event date
Jun 9, 2009
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)