Towards Implementing Free Will - Bruce Edmonds
Thus the next stage is to include the operators of variation in the evolutionary process. In the Koza's original GP algorithm there are only two operators: propagation and tree-crossover. Instead of these two operators I suggest that the population of operators themselves are specified as trees following . These operators are computationally interpreted so they act upon strategies in the base population to produce new variations. The operators are allocated fitness indirectly from the fitnesses of the strategies they produce using the "bucket-brigade" algorithm of Holland  or similar (such as that of Baum , which is better motivated).
To complete the architecture we set the population of operators to also operate on themselves in order to drive the production of new operators. Now the decision making processes (including the processes to produce the processes etc.) are generated internally, in response to the twin evolutionary pressures of deciding what to do to further the agents goals (in this case profit) and avoiding being predictable to other agents. This is illustrated in figure 1.
Figure 1. One step of a meta-genetic evolutionary process
Generated with CERN WebMaker