The Introduction of Learning into the Modelling of Boundedly Rational Economic Agents using the Genetic Programming Paradigm (Title Page)

It is argued that the credible modelling of economic agents from a bounded rationality perspective, implies a certain difference of approach from those involved in designing agents for a specific task or environment. Some of the ramifications of this are that learning in the resulting models can be closely related to the Genetic Programming paradigm. This approach is then compared with a BDI framework. The possibilities for integration of deductive logic- based approaches and evolutionary approaches using the GP paradigm are suggested. The beginnings of a formalism for such agents is outlined and an example application of an agent seeking to maximise its utility by modelling its own utility function is briefly described.