Building Agents with Memory: An Approach using Genetically Programmed Networks



To achieve a high degree of autonomy, an
agent usually needs some kind of memory mechanism. In
this article we present a new approach to the evolution
of agents with memory, based on the use of Genetically
Programmed Networks. These are connectionist structures
where each node has an associated program,
evolved using genetic programming. Genetically Programmed
Networks can easily be evolved into agents
with very different architectures. We present experimental
results from evolving Genetically Programmed Networks
as neural networks, distributed programs and
rule-based systems capable of solving problems where
the use of memory by the agent is essential. Comparisons
are made between the performance of these solutions
and the performance of solutions obtained by other
evolutionary strategies used to evolve agents with memory


Genetic Programming


CEC 99, July 1999

PDF File

Cited by

Year 2003 : 1 citations

 J. T. Alander , Indexed Bibliography of Genetic Algorithms and Artificial Intelligence. Report Series No. 94-1-AI, Department of Electrical Engineering and Production Economics, University of Vaasa, 2003.