@@ -21,7 +21,7 @@ For more information on these see [Genetic Operators](#Genetic-Operators)
Evolutionary Phases represent an evolving phase [Evolutionary Phases](#Evolutionary-Phases).
Many of these phases can be stacked together.
This enables to first evolve individuals
This enables to first evolve simpler solutions then continue to evolve complex ones.
### Genetic Operators
Genetic operators are used to change the genome of individuals or to produce new individuals by combining the genome of multiple individuals.
...
...
@@ -46,7 +46,7 @@ ONLY THESE GENES WILL BE USED IN THE FUTURE.
Therefore an operator should always append its new genes to the ```new_population``` list.
He can remove items from the list but then the size of the population will be shrinked.
Examples can be viewed in the genetic operator definition file.
They will be imported, defined and used in the config file.
They will be imported, defined and used in the config file by the user.
### Evolutionary Phases
...
...
@@ -82,7 +82,12 @@ This should be returned.
# Todos
- provide a user Documentation that covers and explain all needed steps to define own: Phases, Operators, Experiments
- implement a call to the experiment that handles how to save the fittest gene when evolution is finished.
- this has to be user defined and will save the gene into a users usable format for further use
- implement island fusion at user definable time frames in the evolution
- provide a standart fusion module that can always be used
- provide an interface that can be used, like the genetic operators, to allow for user definable fusion rule stacks
- allow for genes to be a user defined type, not hardcoded np.bool_ (int or string makes it much easier for some experiments, though they are binary coded in a computer anyway...)
