Decentralized control in the pursuit domain
Identifieur interne : 003907 ( Crin/Curation ); précédent : 003906; suivant : 003908Decentralized control in the pursuit domain
Auteurs : Raghav ArasSource :
English descriptors
- KwdEn :
Abstract
We study the prey-predator problem as a multi-agent system (MAS). We consider an hierarchical approach to searching optimal policies for each agent to capture the prey. In particular, we imagine decomposition of the state-space, and of the "situation" space. In other words, we consider an hierarchy of policies, the agent following the one which is most appropriate for his current state-space and for the situation in that state-space.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: Pour aller vers cette notice dans l'étape Curation :003907
Links to Exploration step
CRIN:aras03aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="233">Decentralized control in the pursuit domain</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:aras03a</idno>
<date when="2003" year="2003">2003</date>
<idno type="wicri:Area/Crin/Corpus">003907</idno>
<idno type="wicri:Area/Crin/Curation">003907</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003907</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Decentralized control in the pursuit domain</title>
<author><name sortKey="Aras, Raghav" sort="Aras, Raghav" uniqKey="Aras R" first="Raghav" last="Aras">Raghav Aras</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>hierarchical approach</term>
<term>markov decision processes</term>
<term>mas</term>
<term>mdp</term>
<term>planning</term>
<term>prey-predator</term>
<term>reinforcement learning</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="1083">We study the prey-predator problem as a multi-agent system (MAS). We consider an hierarchical approach to searching optimal policies for each agent to capture the prey. In particular, we imagine decomposition of the state-space, and of the "situation" space. In other words, we consider an hierarchy of policies, the agent following the one which is most appropriate for his current state-space and for the situation in that state-space.</div>
</front>
</TEI>
<BibTex type="techreport"><ref>aras03a</ref>
<crinnumber>A03-R-171</crinnumber>
<equipe>MAIA</equipe>
<author><e>Aras, Raghav</e>
</author>
<title>Decentralized control in the pursuit domain</title>
<institution>LORIA INRIA-Lorraine</institution>
<year>2003</year>
<type>Stage de DEA</type>
<month>Jul</month>
<keywords><e>reinforcement learning</e>
<e>markov decision processes</e>
<e>mdp</e>
<e>mas</e>
<e>prey-predator</e>
<e>planning</e>
<e>hierarchical approach</e>
</keywords>
<abstract>We study the prey-predator problem as a multi-agent system (MAS). We consider an hierarchical approach to searching optimal policies for each agent to capture the prey. In particular, we imagine decomposition of the state-space, and of the "situation" space. In other words, we consider an hierarchy of policies, the agent following the one which is most appropriate for his current state-space and for the situation in that state-space.</abstract>
</BibTex>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Crin/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 003907 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Curation/biblio.hfd -nk 003907 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Crin |étape= Curation |type= RBID |clé= CRIN:aras03a |texte= Decentralized control in the pursuit domain }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |