Parallel asynchronous distributed computations of optimal control in large state space Markov Decision Processes
Identifieur interne : 003B96 ( Crin/Curation ); précédent : 003B95; suivant : 003B97Parallel asynchronous distributed computations of optimal control in large state space Markov Decision Processes
Auteurs : Bruno ScherrerSource :
English descriptors
- KwdEn :
Abstract
This paper emphasizes the link between parallel asynchronous distributed computations (PADC) and Markov Decision Processes (MDPs), which are a powerful generic model for computing optimal control. We review some results arguing that reasonably small state space MDPs can be solved with PADC. We then propose a solution for extending these results when the state space is large. This shows that difficult optimal control problems have natural neural network-like solutions and suggests a general methodology for constructing neural networks.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: Pour aller vers cette notice dans l'étape Curation :003B96
Links to Exploration step
CRIN:scherrer03dLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="392">Parallel asynchronous distributed computations of optimal control in large state space Markov Decision Processes</title></titleStmt><publicationStmt><idno type="RBID">CRIN:scherrer03d</idno><date when="2003" year="2003">2003</date><idno type="wicri:Area/Crin/Corpus">003B96</idno><idno type="wicri:Area/Crin/Curation">003B96</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003B96</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Parallel asynchronous distributed computations of optimal control in large state space Markov Decision Processes</title><author><name sortKey="Scherrer, Bruno" sort="Scherrer, Bruno" uniqKey="Scherrer B" first="Bruno" last="Scherrer">Bruno Scherrer</name></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>artificial neural network</term><term>markovian decision process</term><term>optimal control</term><term>parallel asynchronous distributed computations</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="1072">This paper emphasizes the link between parallel asynchronous distributed computations (PADC) and Markov Decision Processes (MDPs), which are a powerful generic model for computing optimal control. We review some results arguing that reasonably small state space MDPs can be solved with PADC. We then propose a solution for extending these results when the state space is large. This shows that difficult optimal control problems have natural neural network-like solutions and suggests a general methodology for constructing neural networks.</div></front></TEI><BibTex type="inproceedings"><ref>scherrer03d</ref><crinnumber>A03-R-474</crinnumber><category>3</category><equipe>CORTEX</equipe><author><e>Scherrer, Bruno</e></author><title>Parallel asynchronous distributed computations of optimal control in large state space Markov Decision Processes</title><booktitle>{11th European Symposium on Artificial Neural Networks - ESANN'03, Bruges, Belgique}</booktitle><year>2003</year><month>Apr</month><keywords><e>parallel asynchronous distributed computations</e><e>markovian decision process</e><e>optimal control</e><e>artificial neural network</e></keywords><abstract>This paper emphasizes the link between parallel asynchronous distributed computations (PADC) and Markov Decision Processes (MDPs), which are a powerful generic model for computing optimal control. We review some results arguing that reasonably small state space MDPs can be solved with PADC. We then propose a solution for extending these results when the state space is large. This shows that difficult optimal control problems have natural neural network-like solutions and suggests a general methodology for constructing neural networks.</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 003B96 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Curation/biblio.hfd -nk 003B96 | 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:scherrer03d
|texte= Parallel asynchronous distributed computations of optimal control in large state space Markov Decision Processes
}}
| This area was generated with Dilib version V0.6.33. |  |