Genetic algorithms have increasingly been applied to economics since the pioneering work by John H. Miller in 1986.
The result is the agents converge within the area of the rational expectations (RATEX) equilibrium for the stable and unstable case.
In social learning, each firm is endowed with a single string which is used as its quantity production decision.
In the individual learning case, agents are endowed with a pool of strings.
After the offspring pool is generated, hypothetical fitness values are calculated.