Analysis of emergent properties in a hybrid bio-inspired architecture for cognitive agents
Contingut de l'obra
Contingut de l'obra
Registre bibliogràfic
Registre
- Títol: Analysis of emergent properties in a hybrid bio-inspired architecture for cognitive agents
- Autor: Romero López, Oscar Javier; Antonio Jiménez, Angélica de
- Publicació original: 2007
- Descripció física: PDF
-
Nota general:
-
In this work, a hybrid, self-configurable, multilayered and evolutio-nary architecture for cognitive agents is developed. Each layer of the subsump-tion architecture is modeled by one different Machine Learning System MLS based on bio-inspired techniques. In this research an evolutionary mechanism supported on Gene Expression Programming to self-configure the behaviour arbitration between layers is suggested.
In addition, a co-evolutionary mechan-ism to evolve behaviours in an independent and parallel fashion is used. The proposed approach was tested in an animat environment using a multi-agent platform and it exhibited several learning capabilities and emergent properties for self-configuring internal agent’s architecture.
-
In this work, a hybrid, self-configurable, multilayered and evolutio-nary architecture for cognitive agents is developed. Each layer of the subsump-tion architecture is modeled by one different Machine Learning System MLS based on bio-inspired techniques. In this research an evolutionary mechanism supported on Gene Expression Programming to self-configure the behaviour arbitration between layers is suggested.
- Notes de reproducció original: Digitalización realizada por la Biblioteca Virtual del Banco de la República (Colombia)
-
Notes:
- Resum: Artificial immune systems; Cognitive science.; Connectionist Q-Learning; Extended classifier systems; gene Expression programming; Hybrid behaviour Co-evolution; Subsumption architecture
- © Derechos reservados del autor
- Colfuturo
- Forma/gènere: text
- Idioma: inglés
- Institució origen: Biblioteca Virtual del Banco de la República
-
Encapçalament de matèria: