Hybrid behaviour orchestration in a multilayered cognitive architecture using an evolutionary approach

Managing and arbitrating behaviours, processes and components in multilayered cognitive architectures when a huge amount of environmental variables are changing continuously with increasing complexity, ensue in a very comprehensive task. The presented framework proposes an hybrid cognitive architect...

Descripción completa

Detalles Bibliográficos
Autor Principal: Romero López, Oscar Javier; Antonio Jiménez, Angélica de
Formato: Artículo (Article)
Lenguaje:Desconocido (Unknown)
Publicado: 2008
Materias:
Acceso en línea:http://babel.banrepcultural.org/cdm/ref/collection/p17054coll23/id/550
id ir-p17054coll23-550
recordtype dspace
spelling ir-p17054coll23-5502020-09-29 Hybrid behaviour orchestration in a multilayered cognitive architecture using an evolutionary approach Romero López, Oscar Javier; Antonio Jiménez, Angélica de Managing and arbitrating behaviours, processes and components in multilayered cognitive architectures when a huge amount of environmental variables are changing continuously with increasing complexity, ensue in a very comprehensive task. The presented framework proposes an hybrid cognitive architecture that relies on subsumption theory and includes some important extensions. These extensions can be condensed in inclusion of learning capabilities through bio-inspired reinforcement machine learning systems, an evolutionary mechanism based on gene expression programming to self-configure the behaviour arbitration between layers, a co-evolutionary mechanism to evolve behaviour repertories in a parallel fashion and finally, an aggregation mechanism to combine the learning algorithms outputs to improve the learning quality and increase the robustness and fault tolerance ability of the cognitive agent. The proposed architecture was proved in an animat environment using a multi-agent platform where several learning capabilities and emergent properties for self-configuring internal agent’s architecture arise. Algorithms outputs; Cognitive agent; Hybrid cognitive architecture; Multilayered cognitive architectures Tecnología; Tecnología / Ingeniería y operaciones afines 2008 PDF Artículo ENG - Inglés Colfuturo © Derechos reservados del autor http://babel.banrepcultural.org/cdm/ref/collection/p17054coll23/id/550
institution Biblioteca Virtual Banco de la República - Colecciones digitales
collection Custom
language Desconocido (Unknown)
topic Algorithms outputs; Cognitive agent; Hybrid cognitive architecture; Multilayered cognitive architectures
Tecnología; Tecnología / Ingeniería y operaciones afines
spellingShingle Algorithms outputs; Cognitive agent; Hybrid cognitive architecture; Multilayered cognitive architectures
Tecnología; Tecnología / Ingeniería y operaciones afines
Romero López, Oscar Javier; Antonio Jiménez, Angélica de
Hybrid behaviour orchestration in a multilayered cognitive architecture using an evolutionary approach
description Managing and arbitrating behaviours, processes and components in multilayered cognitive architectures when a huge amount of environmental variables are changing continuously with increasing complexity, ensue in a very comprehensive task. The presented framework proposes an hybrid cognitive architecture that relies on subsumption theory and includes some important extensions. These extensions can be condensed in inclusion of learning capabilities through bio-inspired reinforcement machine learning systems, an evolutionary mechanism based on gene expression programming to self-configure the behaviour arbitration between layers, a co-evolutionary mechanism to evolve behaviour repertories in a parallel fashion and finally, an aggregation mechanism to combine the learning algorithms outputs to improve the learning quality and increase the robustness and fault tolerance ability of the cognitive agent. The proposed architecture was proved in an animat environment using a multi-agent platform where several learning capabilities and emergent properties for self-configuring internal agent’s architecture arise.
format Artículo (Article)
author Romero López, Oscar Javier; Antonio Jiménez, Angélica de
author_facet Romero López, Oscar Javier; Antonio Jiménez, Angélica de
author_sort Romero López, Oscar Javier; Antonio Jiménez, Angélica de
title Hybrid behaviour orchestration in a multilayered cognitive architecture using an evolutionary approach
title_short Hybrid behaviour orchestration in a multilayered cognitive architecture using an evolutionary approach
title_full Hybrid behaviour orchestration in a multilayered cognitive architecture using an evolutionary approach
title_fullStr Hybrid behaviour orchestration in a multilayered cognitive architecture using an evolutionary approach
title_full_unstemmed Hybrid behaviour orchestration in a multilayered cognitive architecture using an evolutionary approach
title_sort hybrid behaviour orchestration in a multilayered cognitive architecture using an evolutionary approach
publishDate 2008
url http://babel.banrepcultural.org/cdm/ref/collection/p17054coll23/id/550
_version_ 1682459981531578368
score 11,577895