Learning by Collaboration in Intelligent Autonomous Systems

Very few learning systems applied to problem solving have focused on learning operator definitions from the interaction with a completely unknown environment. Autonomous Intelligent Systems (AIS) deal with that issue by means of architectures where learning is achieved by establishing plans, executi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ierache, Jorge Salvador, García Martínez, Ramón, De Giusti, Armando Eduardo
Formato:	Objeto de conferencia
Lenguaje:	Español
Publicado:	2010
Materias:	Ciencias Informáticas Artificial intelligence
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/124419
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-124419
record_format	dspace
institution	Universidad Nacional de La Plata
institution_str	I-19
repository_str	R-120
collection	SEDICI (UNLP)
language	Español
topic	Ciencias Informáticas Artificial intelligence
spellingShingle	Ciencias Informáticas Artificial intelligence Ierache, Jorge Salvador García Martínez, Ramón De Giusti, Armando Eduardo Learning by Collaboration in Intelligent Autonomous Systems
topic_facet	Ciencias Informáticas Artificial intelligence
description	Very few learning systems applied to problem solving have focused on learning operator definitions from the interaction with a completely unknown environment. Autonomous Intelligent Systems (AIS) deal with that issue by means of architectures where learning is achieved by establishing plans, executing those plans in the environment, analyzing the results of the execution, and combining new evidence with prior evidence. This paper proposes a selective mechanism of learning allowing an AIS to learn new operators by receiving them from another AIS in a higher stage in the Learning Life Cycle (LLC) with more cycles of interaction in the environment. The proposed collaboration mechanism also considers how to deal with theory ponderation (operators ponderation) and how to include the new operators (provided for) in the set of theories of the receiver AIS. The experimental results show how using collaboration-based learning among AIS provides a better percentage of successful plans, plus an improved convergence rate, than the individual AIS alone.
format	Objeto de conferencia Objeto de conferencia
author	Ierache, Jorge Salvador García Martínez, Ramón De Giusti, Armando Eduardo
author_facet	Ierache, Jorge Salvador García Martínez, Ramón De Giusti, Armando Eduardo
author_sort	Ierache, Jorge Salvador
title	Learning by Collaboration in Intelligent Autonomous Systems
title_short	Learning by Collaboration in Intelligent Autonomous Systems
title_full	Learning by Collaboration in Intelligent Autonomous Systems
title_fullStr	Learning by Collaboration in Intelligent Autonomous Systems
title_full_unstemmed	Learning by Collaboration in Intelligent Autonomous Systems
title_sort	learning by collaboration in intelligent autonomous systems
publishDate	2010
url	http://sedici.unlp.edu.ar/handle/10915/124419
work_keys_str_mv	AT ierachejorgesalvador learningbycollaborationinintelligentautonomoussystems AT garciamartinezramon learningbycollaborationinintelligentautonomoussystems AT degiustiarmandoeduardo learningbycollaborationinintelligentautonomoussystems
bdutipo_str	Repositorios
_version_	1764820450321367040

Learning by Collaboration in Intelligent Autonomous Systems

Ejemplares similares