ec.simple.README Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of ecj Show documentation

ECJ, A Java-based Evolutionary Computation Research System. ECJ is a research EC system written in Java. It was designed to be highly flexible, with nearly all classes (and all of their settings) dynamically determined at runtime by a user-provided parameter file. All structures in the system are arranged to be easily modifiable. Even so, the system was designed with an eye toward efficiency. ECJ is developed at George Mason University's ECLab Evolutionary Computation Laboratory. The software has nothing to do with its initials' namesake, Evolutionary Computation Journal. ECJ's sister project is MASON, a multi-agent simulation system which dovetails with ECJ nicely.

The newest version!

ec/simple/ contains typical implementations of the abstract forms found in ec/.
Specifically, ec/simple defines generational evolution common in genetic
algorithms, plus some simple statistics modules sufficient to do common work.

The simple.params file is used by a wide range of applications and other tools
as a basic starting point.



The classes are:



ec.simple.SimpleEvolutionState

Performs generational evolution.


ec.simple.SimpleEvaluator

Performs simple multithreaded evaluation of populations by, for each subpopulation,
breaking the subpopulation into N chunks of even size and handing each chunk to
a separate thread to evaluate.


ec.simple.SimpleBreeder

Performs simple multithreaded breeding of populations by, for each subpopulation,
breaking the subpopulation into N chunks of even size and handing each chunk to
a separate thread to fill with individuals generated from breeding pipelines.
SimpleBreeder also has an optional elitism function: the best M individuals in each
subpopulation are advanced to the next generation automatically.


ec.simple.SimpleExchanger
ec.simple.SimpleFinisher

Implementations of Exchanger and Finisher which do nothing at all.


ec.simple.SimpleInitializer

A basic initializer which simply calls populate() on the Population to cause it to
fill itself with new individuals.  Note that certain representations have their own
required subclass of SimpleInitializer which does other minor duties as well.


ec.simple.SimpleProblemForm

An interface which defines how basic, non-coevolutionary, single-individual
fitness evaluation is perfomed.  Your Problem subclass will probably be required
to implement this interface.


ec.simple.SimpleFitness

A basic single-objective fitness class which defines better fitnesses as ones which
have higher values.  In some cases you may wish to restrict such fitness values
to be positive.


ec.simple.SimpleStatistics

A basic Statistics object which prints out the best individual of generation, for
each generation, plus the best individual of run at the end.


ec.simple.SimpleShortStatistics

A basic Statistics object which prints out, one line per generation, a variety of
easily parsed statistical information about that generation's results.