ec.gp.breed
Class MutateDemotePipeline

java.lang.Object
  extended by ec.BreedingSource
      extended by ec.BreedingPipeline
          extended by ec.gp.GPBreedingPipeline
              extended by ec.gp.breed.MutateDemotePipeline
All Implemented Interfaces:
Prototype, Setup, SteadyStateBSourceForm, RandomChoiceChooser, java.io.Serializable, java.lang.Cloneable

public class MutateDemotePipeline
extends GPBreedingPipeline

MutateDemotePipeline works very similarly to the DemoteNode algorithm described in Kumar Chellapilla, "A Preliminary Investigation into Evolving Modular Programs without Subtree Crossover", GP98, and is also similar to the "insertion" operator found in Una-May O'Reilly's thesis, "An Analysis of Genetic Programming".

MutateDemotePipeline tries picks a random tree, then picks randomly from all the demotable nodes in the tree, and demotes one. If its chosen tree has no demotable nodes, or demoting its chosen demotable node would make the tree too deep, it repeats the choose-tree-then-choose-node process. If after tries times it has failed to find a valid tree and demotable node, it gives up and simply copies the individual.

"Demotion" means to take a node n and insert a new node m between n and n's parent. n becomes a child of m; the place where it becomes a child is determined at random from all the type-compatible slots of m. The other child slots of m are filled with randomly-generated terminals. Chellapilla's version of the algorithm always places n in child slot 0 of m. Because this would be unneccessarily restrictive on strong typing, MutateDemotePipeline instead picks the slot at random from all available valid choices.

A "Demotable" node means a node which is capable of demotion given the existing function set. In general to demote a node foo, there must exist in the function set a nonterminal whose return type is type-compatible with the child slot foo holds in its parent; this nonterminal must also have a child slot which is type-compatible with foo's return type.

This method is very expensive in searching nodes for "demotability". However, if the number of types is 1 (the GP run is typeless) then the type-constraint-checking code is bypassed and the method runs a little faster.

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.maxdepth
int >= 1
(maximum valid depth of a mutated tree)
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.mutate-demote

Version:
1.0
Author:
Sean Luke
See Also:
Serialized Form

Field Summary
static int NUM_SOURCES
           
static java.lang.String P_MAXDEPTH
           
static java.lang.String P_MUTATEDEMOTE
           
static java.lang.String P_NUM_TRIES
           
 
Fields inherited from class ec.gp.GPBreedingPipeline
P_NODESELECTOR, P_TREE, TREE_UNFIXED
 
Fields inherited from class ec.BreedingPipeline
DYNAMIC_SOURCES, mybase, P_NUMSOURCES, P_SOURCE, sources, V_SAME
 
Fields inherited from class ec.BreedingSource
CHECKBOUNDARY, DEFAULT_PRODUCED, NO_PROBABILITY, P_PROB, probability, UNUSED
 
Constructor Summary
MutateDemotePipeline()
           
 
Method Summary
 java.lang.Object clone()
          Creates a new individual cloned from a prototype, and suitable to begin use in its own evolutionary context.
 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.
 
Methods inherited from class ec.gp.GPBreedingPipeline
produces
 
Methods inherited from class ec.BreedingPipeline
finishProducing, individualReplaced, maxChildProduction, minChildProduction, preparePipeline, prepareToProduce, sourcesAreProperForm, typicalIndsProduced
 
Methods inherited from class ec.BreedingSource
getProbability, pickRandom, setProbability, setupProbabilities
 
Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

P_MUTATEDEMOTE

public static final java.lang.String P_MUTATEDEMOTE
See Also:
Constant Field Values

P_NUM_TRIES

public static final java.lang.String P_NUM_TRIES
See Also:
Constant Field Values

P_MAXDEPTH

public static final java.lang.String P_MAXDEPTH
See Also:
Constant Field Values

NUM_SOURCES

public static final int NUM_SOURCES
See Also:
Constant Field Values
Constructor Detail

MutateDemotePipeline

public MutateDemotePipeline()
Method Detail

defaultBase

public Parameter defaultBase()
Description copied from interface: Prototype
Returns the default base for this prototype. This should generally be implemented by building off of the static base() method on the DefaultsForm object for the prototype's package. This should be callable during setup(...).


numSources

public int numSources()
Description copied from class: BreedingPipeline
Returns the number of sources to this pipeline. Called during BreedingPipeline's setup. Be sure to return a value > 0, or DYNAMIC_SOURCES which indicates that setup should check the parameter file for the parameter "num-sources" to make its determination.

Specified by:
numSources in class BreedingPipeline

setup

public void setup(EvolutionState state,
                  Parameter base)
Description copied from class: BreedingSource
Sets up the BreedingPipeline. You can use state.output.error here because the top-level caller promises to call exitIfErrors() after calling setup. Note that probability might get modified again by an external source if it doesn't normalize right.

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}.

Specified by:
setup in interface Prototype
Specified by:
setup in interface Setup
Overrides:
setup in class BreedingPipeline
See Also:
Prototype.setup(EvolutionState,Parameter)

clone

public java.lang.Object clone()
Description copied from interface: Prototype
Creates a new individual cloned from a prototype, and suitable to begin use in its own evolutionary context.

Typically this should be a full "deep" clone. However, you may share certain elements with other objects rather than clone hem, depending on the situation:

Implementations.

Specified by:
clone in interface Prototype
Overrides:
clone in class BreedingPipeline

produce

public int produce(int min,
                   int max,
                   int start,
                   int subpopulation,
                   Individual[] inds,
                   EvolutionState state,
                   int thread)
Description copied from class: BreedingSource
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. max must be >= min, and min must be >= 1. For example, crossover might typically produce two individuals, tournament selection might typically produce a single individual, etc.

Specified by:
produce in class BreedingSource