Self-organized and Evolvable Cognitive Architecture for Intelligent Agents and Multi-Agent Systems
Integrating different kinds of micro-theories of cognition in intelligent systems when a huge amount of variables are changing continuously, with increasing complexity, is a very exhaustive and complicated task. Our approach proposes a hybrid cognitive architecture that relies on the integration of emergent and cognitivist approaches using evolutionary strategies, in order to combine implicit and explicit knowledge representations necessary to develop cognitive skills. The proposed architecture includes a cognitive level controlled by autopoietic machines and artificial immune systems based on genetic algorithms, giving it a significant degree of plasticity. Furthermore, we propose an attention module which includes an evolutionary programming mechanism in charge of orchestrating the hierarchical relations among specialized behaviors, taking into consideration the global workspace theory for consciousness. Additionally, a co-evolutionary mechanism is proposed to propagate knowledge among cognitive agents on the basis of memetic engineering. As a result, several properties of self-organization and adaptability emerged when the proposed architecture was tested in an animat environment, using a multi-agent platform.
KeywordsCognitive architectures gene expression programming artificial immune systems neural nets memetics
Unable to display preview. Download preview PDF.
- 2.Berthoz, A.: The Brain’s Sense of Movement. Harvard Univ. Press, Cambridge (2000)Google Scholar
- 3.Vernon, D., Metta, G., Sandini, G.: A survey of artificial cognitive systems: Implications for the autonomous development of mental capabilities in computational agents. IEEE Trans. Evolutionary Computation 11(2) (April 2007)Google Scholar
- 4.Rosenbloom, P., Laird, J., Newell, A. (eds.): The Soar Papers: Research on integrated intell. MIT Press, Cambridge (1993)Google Scholar
- 9.Cassimatis, N.L.: Adaptive Algorithmic Hybrids for Human-Level Artificial Intelligence. Advances in Arti. Intell. (2007)Google Scholar
- 10.Franklin, S.: The LIDA architecture: Adding new modes of learning to an intelligent, autonomous, software agent. In: Proc. of the Int. Conf. on Integrated Design and Process Technology (2006)Google Scholar
- 11.Maturana, H.R., Varela, F.J.: Autopoiesis and Cognition: The Realization of the Living. Boston Studies on the Philosophy of Science. D. Reidel Publishing Company, Dordrecht (1980)Google Scholar
- 13.Rumelhart, D., McClelland, J.: Parallel Distributed Processing: Explorations in the Microstructures of Cognition. MIT Press, Cambridge (1986)Google Scholar
- 14.Watkins, C., Dayan, P.: Q-learning. Machine Learning 3, 279–292 (1992)Google Scholar
- 15.de Castro, L.N., Timmis, J.: Artificial Immune Systems: A New Computational Intelligence Approach (2002)Google Scholar
- 16.Dawkins, R.: The Selfish Gene. Oxford University Press, Oxford (1989)Google Scholar
- 17.Romero, D., Niño, L.: An Immune-based Multilayered Cognitive Model for Autonomous Navigation, CEC, Vancouver, pp. 1115–1122 (2006)Google Scholar