Modular Multiobjective (Hyper) Neuro-Evolution of Augmenting Topologies + MAP-Elites: Java code for evolving intelligent agents in Ms. Pac-Man, Tetris, and more, as well as code for Procedural Content Generation in Mario, Zelda, Minecraft, and more!
Issue #911 is to save the whole archive of Minecraft shapes at the end, but this doesn't help with runs using pure fitness, such as NSGA2. So, we need a similar solution that saves the whole final population as lists of blocks (rather than xml genotypes, which is what it currently does).
I've put an if statement in the close method of MuLambda which will be part of an upcoming commit. Save the population there.
Issue #911 is to save the whole archive of Minecraft shapes at the end, but this doesn't help with runs using pure fitness, such as NSGA2. So, we need a similar solution that saves the whole final population as lists of blocks (rather than xml genotypes, which is what it currently does).
I've put an if statement in the
close
method ofMuLambda
which will be part of an upcoming commit. Save the population there.