Adaptive Combination of Behaviors in an Agent
Identifieur interne : 003266 ( Crin/Corpus ); précédent : 003265; suivant : 003267Adaptive Combination of Behaviors in an Agent
Auteurs : Olivier Buffet ; Alain Dutech ; François CharpilletSource :
English descriptors
- KwdEn :
Abstract
Agents are of interest mainly when confronted with complex tasks. We propose a methodology for the automated design of such agents (in the framework of Markov Decision Processes) in the case where the global task can be decomposed into simpler -possibly concurrent- sub-tasks. This is accomplished by automatically combining basic behaviors using Reinforcement Learning methods. \correction[Basic behaviors]{The main idea is to build a global policy using a weighted combination of basic policies, the weights being learned by the agent (using Simulated Annealing in our case). These basic behaviors} can either be learned or reused from previous tasks since they will not need to be tuned to the new task. Furthermore, the agents designed by our methodology are highly scalable as, without further refinement of the global behavior, they can automatically combine several instances of the same basic behavior to take into account concurrent occurences of the same subtask.
Links to Exploration step
CRIN:buffet02bLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="432">Adaptive Combination of Behaviors in an Agent</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:buffet02b</idno>
<date when="2002" year="2002">2002</date>
<idno type="wicri:Area/Crin/Corpus">003266</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Adaptive Combination of Behaviors in an Agent</title>
<author><name sortKey="Buffet, Olivier" sort="Buffet, Olivier" uniqKey="Buffet O" first="Olivier" last="Buffet">Olivier Buffet</name>
</author>
<author><name sortKey="Dutech, Alain" sort="Dutech, Alain" uniqKey="Dutech A" first="Alain" last="Dutech">Alain Dutech</name>
</author>
<author><name sortKey="Charpillet, Francois" sort="Charpillet, Francois" uniqKey="Charpillet F" first="François" last="Charpillet">François Charpillet</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>adaptation</term>
<term>reinforcement learning</term>
<term>scalability</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="3520">Agents are of interest mainly when confronted with complex tasks. We propose a methodology for the automated design of such agents (in the framework of Markov Decision Processes) in the case where the global task can be decomposed into simpler -possibly concurrent- sub-tasks. This is accomplished by automatically combining basic behaviors using Reinforcement Learning methods. \correction[Basic behaviors]{The main idea is to build a global policy using a weighted combination of basic policies, the weights being learned by the agent (using Simulated Annealing in our case). These basic behaviors} can either be learned or reused from previous tasks since they will not need to be tuned to the new task. Furthermore, the agents designed by our methodology are highly scalable as, without further refinement of the global behavior, they can automatically combine several instances of the same basic behavior to take into account concurrent occurences of the same subtask.</div>
</front>
</TEI>
<BibTex type="inproceedings"><ref>buffet02b</ref>
<crinnumber>A02-R-086</crinnumber>
<category>3</category>
<equipe>MAIA</equipe>
<author><e>Buffet, Olivier</e>
<e>Dutech, Alain</e>
<e>Charpillet, François</e>
</author>
<title>Adaptive Combination of Behaviors in an Agent</title>
<booktitle>{European Conference on Artificial Intelligence - ECAI'02, Lyon, France}</booktitle>
<year>2002</year>
<pages>48-52</pages>
<month>Jul</month>
<keywords><e>reinforcement learning</e>
<e>scalability</e>
<e>adaptation</e>
</keywords>
<abstract>Agents are of interest mainly when confronted with complex tasks. We propose a methodology for the automated design of such agents (in the framework of Markov Decision Processes) in the case where the global task can be decomposed into simpler -possibly concurrent- sub-tasks. This is accomplished by automatically combining basic behaviors using Reinforcement Learning methods. \correction[Basic behaviors]{The main idea is to build a global policy using a weighted combination of basic policies, the weights being learned by the agent (using Simulated Annealing in our case). These basic behaviors} can either be learned or reused from previous tasks since they will not need to be tuned to the new task. Furthermore, the agents designed by our methodology are highly scalable as, without further refinement of the global behavior, they can automatically combine several instances of the same basic behavior to take into account concurrent occurences of the same subtask.</abstract>
</BibTex>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Crin/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 003266 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Corpus/biblio.hfd -nk 003266 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Crin |étape= Corpus |type= RBID |clé= CRIN:buffet02b |texte= Adaptive Combination of Behaviors in an Agent }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |