In this work, we evaluate an asynchronous population-based algorithms following a pool-based approach. In Pool-based algorithms a collection of heterogeneous worker processes collaborate through a shared population repository. In particular we followed the EvoSpace approach in which workers asynchronously interact with a population pool by taking samples of the population to perform a local search on the samples, to then return newly evolved solutions back to the pool. We benchmark against the BBOB noiseless testbed a hybrid algorithm mixing two kinds or workers: PSO and GA. The results of the asynchronous execution were transformed into files compatible with the Comparing Continuous Optimizer platform. We find that an Pool-based approach outperforms the canonical GA and PSO algorithms in nearly all cases. The results from these tests suggest that a Pool Based approach can be used to implement hybrid algorithms that can improve the performance of single population-based optimization algorithms.

This are the files reporting the experiment.