Expand description
When approacking a (local) optimum in the fitness score, the variation in the population goes down dramatically. The offspring will become clones of the parents and the only factor seeding randomness is the mutation of the offspring. But this remaining randomness might not be selected for, killing of the offspring again. This reduces the efficiency, but also has the risk of local optimum lock-in. To increase the variation in the population, an extension mechanisms can optionally be used
Structs§
- Simulates a cambrian explosion. The controlling metric is fitness score cardinality in the population after selection. When this cardinality drops to the threshold, the full population is mutated the provided number of times, where the Genotype determines whether this is random, relative or scaled.
- Simulates a cambrian explosion. The controlling metric is fitness score cardinality in the population after selection. When this cardinality drops to the threshold, the population is randomly reduced regardless of fitness using the survival_rate (fraction of population).
- A version of MassExtinction, where only an adam and eve of current best chromosomes survive
- The placeholder for when no extension present