[Repast-developer] Genetic Algorithm

[Jeffrey F. <jja...@ch...>]

In the process of coming up with a GA implementation for Repast, I have 
come up one the question, what level make the most sense. Essentially, 
I have devised three different levels that could all make sense in 
their own way. At the lowest level, you could setup a GA that runs for 
each agent evolving an ideal set of behavior values. The next level up 
would evolve the population of agents in order to achieve a "perfect" 
agent. The option would be to have a GA consist of a population of 
models, which would yield a best model.

What level you think would make the most sense for implementation into 
Repast?


-Jeff