public class AnnealedSelection extends SelectionMethod
This works as follows. If there is only one individual in the population, he is selected. Otherwise we pick a random individual from among the individuals other than the first individual. If that random individual is fitter than the first individual, it is selected. Otherwise if that random individual is as fit as the first individual, one of the two is selected at random. Otherwise if the random individual is not as fit as the first individual, it is selected with a probability P = e^((fit(random ind) - fit(first ind)) / t), where t is a TEMPERATURE. Otherwise the first individual is selected.
The temperature starts at a high value >> 0, and is slowly cut down by multiplying it by a CUTDOWN value every generation. When the temperature reaches 0, then the first individual is selected every time.
The selected individual can be cached so the same individual is returned multiple times without being recomputed. This cache is cleared after prepareToProduce(...) is called. Note that this option is not appropriate for Steady State Evolution, which only calls prepareToProduce(...) once.
Typical Number of Individuals Produced Per produce(...) call
Always 1.
Parameters
base.cache bool = true or false (default) |
(should we cache the individual?) |
base.temperature double > 0 (or undefined) |
(annealing start temperature) |
base.cutdown 0.0 <= double >= 1.0 (default is 0.95) |
(annealing cutdown) |
Default Base
select.annealed
Modifier and Type | Field and Description |
---|---|
static java.lang.String |
P_ANNEALED
Default base
|
static java.lang.String |
P_CACHE |
static java.lang.String |
P_CUTDOWN |
static java.lang.String |
P_TEMPERATURE |
static double |
V_CUTDOWN |
INDS_PRODUCED, KEY_PARENTS
NO_PROBABILITY, P_PROB, probability
Constructor and Description |
---|
AnnealedSelection() |
Modifier and Type | Method and Description |
---|---|
void |
cacheBest(int subpopulation,
EvolutionState state,
int thread) |
Parameter |
defaultBase()
Returns the default base for this prototype.
|
void |
prepareToProduce(EvolutionState s,
int subpopulation,
int thread)
A default version of prepareToProduce which does nothing.
|
int |
produce(int subpopulation,
EvolutionState state,
int thread)
An alternative form of "produce" special to Selection Methods;
selects an individual from the given subpopulation and
returns its position in that subpopulation.
|
void |
setup(EvolutionState state,
Parameter base)
Sets up the BreedingPipeline.
|
finishProducing, produce, produces, produceWithoutCloning, typicalIndsProduced
clone, fillStubs, getProbability, pickRandom, preparePipeline, setProbability, setupProbabilities
public static final java.lang.String P_ANNEALED
public static final java.lang.String P_CACHE
public static final java.lang.String P_TEMPERATURE
public static final java.lang.String P_CUTDOWN
public static final double V_CUTDOWN
public Parameter defaultBase()
Prototype
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 BreedingSource
Prototype.setup(EvolutionState,Parameter)
public void prepareToProduce(EvolutionState s, int subpopulation, int thread)
SelectionMethod
prepareToProduce
in class SelectionMethod
public void cacheBest(int subpopulation, EvolutionState state, int thread)
public int produce(int subpopulation, EvolutionState state, int thread)
SelectionMethod
produce
in class SelectionMethod