Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/30081
COMPARTIR / EXPORTAR:
SHARE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Campo DC | Valor | Lengua/Idioma |
---|---|---|
dc.contributor.author | Celaya, Enric | - |
dc.contributor.author | Torras, Carme | - |
dc.contributor.author | Wörgötter, Florentin | - |
dc.contributor.author | Agostini, Alejandro | - |
dc.date.accessioned | 2010-12-15T13:41:55Z | - |
dc.date.available | 2010-12-15T13:41:55Z | - |
dc.date.issued | 2008 | - |
dc.identifier.citation | Technical Report IRI-TR-08-04, Institut de Robòtica i Informàtica Industrial, CSIC-UPC, 2008. | - |
dc.identifier.uri | http://hdl.handle.net/10261/30081 | - |
dc.description.abstract | In this work we propose a learning system to learn on-line an action policy coded in rules using natural human instructions about cause-effect relations in currently observed situations. The instructions only on currently observed situations avoid complicated descriptions of long-run action sequences and complete world dynamics. Human interaction is only required if the system fails to obtain the expected results when applying a rule, or fails to resolve the task with the knowledge acquired so far. | - |
dc.description.sponsorship | This work was supported by the project 'Perception, action & cognition through learning of object-action complexes.' (4915). | - |
dc.language.iso | eng | - |
dc.rights | openAccess | - |
dc.subject | Robot-human interaction | - |
dc.subject | Cause-effect learning | - |
dc.subject | Rule based learning | - |
dc.subject | Intelligent robots and autonomous agents | - |
dc.subject | Machine learning | - |
dc.title | Learning rules from cause-effects explanations | - |
dc.type | informe técnico | - |
dc.type.coar | http://purl.org/coar/resource_type/c_18gh | es_ES |
item.openairetype | informe técnico | - |
item.languageiso639-1 | en | - |
item.grantfulltext | open | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.fulltext | With Fulltext | - |
item.cerifentitytype | Publications | - |
Aparece en las colecciones: | (IRII) Informes y documentos de trabajo |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Learning rules.pdf | 8,62 MB | Adobe PDF | Visualizar/Abrir |
CORE Recommender
Page view(s)
356
checked on 05-may-2024
Download(s)
129
checked on 05-may-2024
Google ScholarTM
Check
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.