The University of Sussex

Brave mobots use representation

Chris Thornton

This paper uses ideas from Machine Learning, Artificial Intelligence and Genetic Algorithms to provide a model of the development of a 'fight-or-flight' response to a simulated agent. This modelled development process involves (simulated) processes of evolution, learning and representation development. The main value of the model is that it provides a clear illustration of how learning processes may lead to the formation of representations, and how these may form the infrastructure for closely-coupled agent/environment interaction.


Download compressed postscript file