Interac-DEC-MDP : Towards the use of interactions in DEC-MDP
Identifieur interne : 003D97 ( Crin/Curation ); précédent : 003D96; suivant : 003D98Interac-DEC-MDP : Towards the use of interactions in DEC-MDP
Auteurs : Vincent Thomas ; Christine Bourjot ; Vincent ChevrierSource :
English descriptors
Abstract
This article presents a new formalism Interac-DEC-MDP whose aim is to introduce the concept of interaction in Decentralized Markov Decision Process and which has been inspired by biology. The aim of this formalism, Interac-DEC-MDP, is to describe and represent interactions among agents. The outcome of interactions is decided collectively by two agents and is in charge of the distribution of local rewards. We have modeled a biological experiment within this formalism. A simple learning algorithm applied on this formalism generates a more efficient collective behavior than without interactions.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: Pour aller vers cette notice dans l'étape Curation :003D97
Links to Exploration step
CRIN:thomas04bLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="140">Interac-DEC-MDP : Towards the use of interactions in DEC-MDP</title></titleStmt><publicationStmt><idno type="RBID">CRIN:thomas04b</idno><date when="2004" year="2004">2004</date><idno type="wicri:Area/Crin/Corpus">003D97</idno><idno type="wicri:Area/Crin/Curation">003D97</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003D97</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Interac-DEC-MDP : Towards the use of interactions in DEC-MDP</title><author><name sortKey="Thomas, Vincent" sort="Thomas, Vincent" uniqKey="Thomas V" first="Vincent" last="Thomas">Vincent Thomas</name></author><author><name sortKey="Bourjot, Christine" sort="Bourjot, Christine" uniqKey="Bourjot C" first="Christine" last="Bourjot">Christine Bourjot</name></author><author><name sortKey="Chevrier, Vincent" sort="Chevrier, Vincent" uniqKey="Chevrier V" first="Vincent" last="Chevrier">Vincent Chevrier</name></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>interaction</term><term>learning</term><term>markov decision process</term><term>multi-agent system</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="2672">This article presents a new formalism Interac-DEC-MDP whose aim is to introduce the concept of interaction in Decentralized Markov Decision Process and which has been inspired by biology. The aim of this formalism, Interac-DEC-MDP, is to describe and represent interactions among agents. The outcome of interactions is decided collectively by two agents and is in charge of the distribution of local rewards. We have modeled a biological experiment within this formalism. A simple learning algorithm applied on this formalism generates a more efficient collective behavior than without interactions.</div></front></TEI><BibTex type="inproceedings"><ref>thomas04b</ref><crinnumber>A04-R-109</crinnumber><category>3</category><equipe>MAIA</equipe><author><e>Thomas, Vincent</e><e>Bourjot, Christine</e><e>Chevrier, Vincent</e></author><title>Interac-DEC-MDP : Towards the use of interactions in DEC-MDP</title><booktitle>{Third International Joint Conference on Autonomous Agents and Multi-Agent Systems - AAMAS'04, New York, USA}</booktitle><year>2004</year><pages>1450-1451</pages><month>Jul</month><keywords><e>markov decision process</e><e>multi-agent system</e><e>interaction</e><e>learning</e></keywords><abstract>This article presents a new formalism Interac-DEC-MDP whose aim is to introduce the concept of interaction in Decentralized Markov Decision Process and which has been inspired by biology. The aim of this formalism, Interac-DEC-MDP, is to describe and represent interactions among agents. The outcome of interactions is decided collectively by two agents and is in charge of the distribution of local rewards. We have modeled a biological experiment within this formalism. A simple learning algorithm applied on this formalism generates a more efficient collective behavior than without interactions.</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 003D97 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Curation/biblio.hfd -nk 003D97 | 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:thomas04b
|texte= Interac-DEC-MDP : Towards the use of interactions in DEC-MDP
}}
| This area was generated with Dilib version V0.6.33. |  |