Predictability of the imitative learning trajectories

TL;DR

This study investigates how the structure of fitness landscapes and search parameters influence the predictability and divergence of imitative learning trajectories, revealing that landscape ruggedness and parameters like population size affect trajectory determinism.

Contribution

It introduces measures for predictability and divergence of learning trajectories and analyzes their dependence on landscape ruggedness and search parameters.

Findings

Predictability is higher in rugged landscapes.

Mean path divergence is influenced by population size and imitation propensity.

Learning trajectories become more deterministic with larger populations and higher imitation rates.

Abstract

The fitness landscape metaphor plays a central role on the modeling of optimizing principles in many research fields, ranging from evolutionary biology, where it was first introduced, to management research. Here we consider the ensemble of trajectories of the imitative learning search, in which agents exchange information on their fitness and imitate the fittest agent in the population aiming at reaching the global maximum of the fitness landscape. We assess the degree to which the starting and ending points determine the learning trajectories using two measures, namely, the predictability that yields the probability that two randomly chosen trajectories are the same, and the mean path divergence that gauges the dissimilarity between two learning trajectories. We find that the predictability is greater in rugged landscapes than in smooth ones. The mean path divergence, however, is strongly affected by the search parameters -- population size and imitation propensity -- that obliterate the influence of the underlying landscape. The learning trajectories become more deterministic, in the sense that there are fewer distinct trajectories and those trajectories are more similar to each other, with increasing population size and imitation propensity. In addition, we find that the roughness of the learning trajectories, which measures the deviation from additivity of the fitness function, is always greater than the roughness estimated over the entire fitness landscape.