It is not entirely clear to me how you guys handle elitism. In your paper (link) you mention "The Nth individual is an unmodified copy of the best individual from the previous generation,...". However, if I understand correctly, in the ga and ga_modified algorithms your workers still evolve the parameters if they sample the first (or last) individual in the population.
In fact I don't immediately see where any of the mentioned 'evaluate top 10 individuals from previous generation on 30 additional episodes' takes place.
I'm just curious because I'm not sure how to handle elitism in a project myself. Thanks in advance :)
Hi,
It is not entirely clear to me how you guys handle elitism. In your paper (link) you mention "The Nth individual is an unmodified copy of the best individual from the previous generation,...". However, if I understand correctly, in the ga and ga_modified algorithms your workers still evolve the parameters if they sample the first (or last) individual in the population.
In fact I don't immediately see where any of the mentioned 'evaluate top 10 individuals from previous generation on 30 additional episodes' takes place.
I'm just curious because I'm not sure how to handle elitism in a project myself. Thanks in advance :)