Learning by Collaboration in Intelligent Autonomous Systems - Artificial Intelligence in Theory and Practice III
Conference Papers Year : 2010

Learning by Collaboration in Intelligent Autonomous Systems

Abstract

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.
Fichier principal
Vignette du fichier
Ierache_WCC_AI_Paper_235.pdf (295.59 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01054598 , version 1 (07-08-2014)

Licence

Identifiers

Cite

Jorge Ierache, Ramón García-Martínez, Armando Giusti. Learning by Collaboration in Intelligent Autonomous Systems. Third IFIP TC12 International Conference on Artificial Intelligence (AI) / Held as Part of World Computer Congress (WCC), Sep 2010, Brisbane, Australia. pp.143-152, ⟨10.1007/978-3-642-15286-3_14⟩. ⟨hal-01054598⟩
303 View
156 Download

Altmetric

Share

More