Discussing the article: "Population optimization algorithms: Resistance to getting stuck in local extrema (Part II)"

[MetaQuotes]

Check out the new article: Population optimization algorithms: Resistance to getting stuck in local extrema (Part II).

We continue our experiment that aims to examine the behavior of population optimization algorithms in the context of their ability to efficiently escape local minima when population diversity is low and reach global maxima. Research results are provided.

Grey Wolf Optimizer (GWO)

C_AO_GWO:50;10
=============================
5 Hilly's; Func runs: 10000; result: 0.5385541648909985
25 Hilly's; Func runs: 10000; result: 0.33060651191769963
500 Hilly's; Func runs: 10000; result: 0.25796885816873344
=============================
5 Forest's; Func runs: 10000; result: 0.33256641908450685
25 Forest's; Func runs: 10000; result: 0.2040563379483599
500 Forest's; Func runs: 10000; result: 0.15278428644972566
=============================
5 Megacity's; Func runs: 10000; result: 0.2784615384615384
25 Megacity's; Func runs: 10000; result: 0.1587692307692308
500 Megacity's; Func runs: 10000; result: 0.133153846153847
=============================
All score: 2.38692

A pack of wolves of the GWO algorithm rushes across the vast expanses of the virtual world, rapidly spreading in all directions on various test functions. This property can be effectively used in the initial iterations, especially if the algorithm is paired with another method that can improve and complement the solutions found. The pack's excellent research abilities speak of their potential, but unfortunately, accuracy in identifying areas remains their weak point. Interestingly, the algorithm showed even better results than in the conventional test with the uniform distribution of agents.

Author: Andrey Dik