Self-Organized and Evolvable Cognitive Architecture for Intelligent Agents and Multi-agent Systems

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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2010 Second International Conference on Computer Engineering and Applications Ročník 1; s. 417 - 421
Hlavní autoři: Javier, Oscar, Lopez, Romero
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.03.2010
Témata:
Artificial Immune Systems
Cognitive Architectures
Environmental management
Evolutionary Approaches
Gene expression
Gene Expression Programming
Genetic programming
Intelligent agent
Intelligent Agents
Learning systems
Machine learning
Machine learning algorithms
Multiagent systems
Parallel programming
Robustness
ISBN:1424460794, 9781424460793
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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 animate environment using a multi-agent platform where several learning capabilities and emergent properties for self-configuring internal agent's architecture arise.
ISBN:1424460794
9781424460793
DOI:10.1109/ICCEA.2010.87