public class RehangPipeline extends GPBreedingPipeline
Important Note: Because it must be free of any constraints by nature, RehangPipeline does not work with strong typing. You must not have more than one type defined in order to use RehangPipeline.
RehangPipeline picks a random tree, then picks randomly from all the nonterminals in the tree other than the root, and rehangs the chosen nonterminal as the new root. If its chosen tree has no nonterminals, it repeats the choose-tree process. If after tries times it has failed to find a tree with nonterminals (other than the root), it gives up and simply copies the individual. As you might guess, determining if a tree has nonterminals is very fast, so tries can be pretty large with little to no detriment to evolution speed.
"Rehanging" is complicated to describe. First, you pick a random child of your chosen nonterminal n, and remove this subtree from the tree. Call this subtree T. Next, you set the nonterminal as a new root; its former parent p now fills the slot left behind by the missing subtree. The p's former parent q now fills the slot left behind by n. q's former parent r now fills the slot left behind by p, and so on. This proceeds all the way up to the old root, which will be left with one empty slot (where its former child was that is now its new parent). This slot is then filled with T
Typical Number of Individuals Produced Per produce(...) call
...as many as the source produces
Number of Sources
1
Parameters
base.tries int >= 1 |
(number of times to try finding valid pairs of nodes) |
base.tree.0 0 < int < (num trees in individuals), if exists |
(tree chosen for mutation; if parameter doesn't exist, tree is picked at random) |
Default Base
gp.breed.rehang
Modifier and Type | Field and Description |
---|---|
static int |
NUM_SOURCES |
static java.lang.String |
P_NUM_TRIES |
static java.lang.String |
P_REHANG |
P_NODESELECTOR, P_TREE, TREE_UNFIXED
DYNAMIC_SOURCES, likelihood, mybase, P_LIKELIHOOD, P_NUMSOURCES, P_SOURCE, sources, V_SAME
NO_PROBABILITY, P_PROB, probability
Constructor and Description |
---|
RehangPipeline() |
Modifier and Type | Method and Description |
---|---|
Parameter |
defaultBase()
Returns the default base for this prototype.
|
int |
numSources()
Returns the number of sources to this pipeline.
|
int |
produce(int min,
int max,
int start,
int subpopulation,
Individual[] inds,
EvolutionState state,
int thread)
Produces n individuals from the given subpopulation
and puts them into inds[start...start+n-1],
where n = Min(Max(q,min),max), where q is the "typical" number of
individuals the BreedingSource produces in one shot, and returns
n.
|
void |
setup(EvolutionState state,
Parameter base)
Sets up the BreedingPipeline.
|
produces
clone, finishProducing, individualReplaced, maxChildProduction, minChildProduction, preparePipeline, prepareToProduce, reproduce, sourcesAreProperForm, typicalIndsProduced
getProbability, pickRandom, setProbability, setupProbabilities
public static final java.lang.String P_REHANG
public static final java.lang.String P_NUM_TRIES
public static final int NUM_SOURCES
public Parameter defaultBase()
Prototype
public int numSources()
BreedingPipeline
numSources
in class BreedingPipeline
public void setup(EvolutionState state, Parameter base)
BreedingSource
The most common modification is to normalize it with some other set of probabilities, then set all of them up in increasing summation; this allows the use of the fast static BreedingSource-picking utility method, BreedingSource.pickRandom(...). In order to use this method, for example, if four breeding source probabilities are {0.3, 0.2, 0.1, 0.4}, then they should get normalized and summed by the outside owners as: {0.3, 0.5, 0.6, 1.0}.
setup
in interface Prototype
setup
in interface Setup
setup
in class BreedingPipeline
Prototype.setup(EvolutionState,Parameter)
public int produce(int min, int max, int start, int subpopulation, Individual[] inds, EvolutionState state, int thread)
BreedingSource
produce
in class BreedingSource