public void TestSpeciateAll_Manhattan()
{
IRandomSource rng = RandomDefaults.CreateRandomSource(0);
var distanceMetric = new ManhattanDistanceMetric();
var speciationStrategy = new GeneticKMeansSpeciationStrategy <double>(distanceMetric, 50, RandomDefaults.CreateRandomSource());
TestSpeciateAll(100, 3, 2, 0.5, distanceMetric, speciationStrategy, rng);
TestSpeciateAll(100, 10, 10, 0.2, distanceMetric, speciationStrategy, rng);
TestSpeciateAll(100, 30, 10, 0.1, distanceMetric, speciationStrategy, rng);
}
public void SpeciateAdd_Manhattan()
{
IRandomSource rng = RandomDefaults.CreateRandomSource(2);
var distanceMetric = new ManhattanDistanceMetric();
var speciationStrategy = new RegularizedGeneticKMeansSpeciationStrategy <double>(distanceMetric, 50, 0.1, 4);
TestSpeciateAdd(100, 3, 2, 0.5, distanceMetric, speciationStrategy, rng, false);
TestSpeciateAdd(100, 10, 10, 0.2, distanceMetric, speciationStrategy, rng, false);
TestSpeciateAdd(100, 30, 10, 0.1, distanceMetric, speciationStrategy, rng, false);
}
/// <summary>
/// Create and return a NeatEvolutionAlgorithm list ready for running the NEAT algorithm/search. Various sub-parts
/// of the algorithm are also constructed and connected up.
/// </summary>
public ModuleNeatEvolutionAlgorithm <NeatGenome>[] CreateEvolutionAlgorithms(int populationSize)
{
// Create the modules.
List <Module> modules = new List <Module>();
for (int i = 0; i < _moduleCount; i++)
{
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetricPitch = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategyPitch = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetricPitch, _parallelOptions);
IDistanceMetric distanceMetricRhythm = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategyRhythm = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetricRhythm, _parallelOptions);
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationPitch =
ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
IComplexityRegulationStrategy complexityRegulationRhythm =
ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
// Create and add a new module with strategies and the evolution parameters.
Module module = new Module((i + 1), _eaParams,
speciationStrategyPitch, speciationStrategyRhythm,
complexityRegulationPitch, complexityRegulationRhythm);
modules.Add(module);
}
// Hook-up the modules with each other in circular order.
// TODO Right now, they are hooked-up in circular order. Check whether it should be done otherwise.
//for (int i = 0; i < modules.Count; i++)
//{
// modules[i].SetParasiteModule(i != modules.Count - 1 ? modules[i + 1] : modules[0], _parasiteCount,
// _championCount, CreateGenomeDecoder());
//}
foreach (var module in modules)
{
module.SetParasiteModules(modules.Except(new List <Module>()
{
module
}).ToList(), _parasiteCount, _championCount, CreateGenomeDecoder(), CreateGenomeDecoder());
}
// Initialize each module.
foreach (var module in modules)
{
var rhythmFactory = CreateGenomeFactory();
var pitchFactory = CreateGenomeFactory();
module.Initialize(rhythmFactory, pitchFactory, populationSize);
}
// Finished. Return the evolution algorithms
return
(modules.Select(m => m.RhythmEvolutionAlgorithm).Concat(modules.Select(m => m.PitchEvolutionAlgorithm)).ToArray());
}
private NeatEvolutionAlgorithm <NeatGenome> GenerateTeam()
{
NeatEvolutionAlgorithmParameters neatParams = new NeatEvolutionAlgorithmParameters();
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(0.4, 1.0, 0.0);
ISpeciationStrategy <NeatGenome> speciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric);
IComplexityRegulationStrategy complexityStrategy = new NullComplexityRegulationStrategy();
return(new NeatEvolutionAlgorithm <NeatGenome>(neatParams, speciationStrategy, complexityStrategy));
}
private NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm_private(IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList, HyperNEAT_Args args = null)
{
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1, 0, 10);
ISpeciationStrategy <NeatGenome> speciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric, _parallelOptions);
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationStrategy = ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
// Create the evolution algorithm.
NeatEvolutionAlgorithm <NeatGenome> retVal = new NeatEvolutionAlgorithm <NeatGenome>(NeatEvolutionAlgorithmParameters, speciationStrategy, complexityRegulationStrategy);
// Genome Decoder
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = null;
if (args == null)
{
genomeDecoder = CreateGenomeDecoder();
}
else
{
genomeDecoder = CreateGenomeDecoder(args);
}
// Create a genome list evaluator. This packages up the genome decoder with the genome evaluator.
IGenomeListEvaluator <NeatGenome> genomeEvaluator = null;
if (_phenomeEvaluator != null)
{
IGenomeListEvaluator <NeatGenome> innerEvaluator = new ParallelGenomeListEvaluator <NeatGenome, IBlackBox>(genomeDecoder, _phenomeEvaluator, _parallelOptions);
// Wrap the list evaluator in a 'selective' evaluator that will only evaluate new genomes. That is, we skip re-evaluating any genomes
// that were in the population in previous generations (elite genomes). This is determined by examining each genome's evaluation info object.
genomeEvaluator = new SelectiveGenomeListEvaluator <NeatGenome>(
innerEvaluator,
SelectiveGenomeListEvaluator <NeatGenome> .CreatePredicate_OnceOnly());
}
else if (_phenomeEvaluators != null)
{
// Use the multi tick evaluator
genomeEvaluator = new TickGenomeListEvaluator <NeatGenome, IBlackBox>(genomeDecoder, _phenomeEvaluators, _phenometickeval_roundRobinManager, _phenometickeval_worldTick);
}
else
{
throw new ApplicationException("One of the phenome evaluators needs to be populated");
}
// Initialize the evolution algorithm.
retVal.Initialize(genomeEvaluator, genomeFactory, genomeList);
// Finished. Return the evolution algorithm
return(retVal);
}
private static void InitialiseSpecies(NeatPopulation <double> neatPop)
{
// Create a speciation strategy instance.
var distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
var speciationStrategy = new Speciation.GeneticKMeans.Parallelized.GeneticKMeansSpeciationStrategy <double>(distanceMetric, 5, 4);
// Apply the speciation strategy.
var genomeComparerDescending = new GenomeComparerDescending(PrimaryFitnessInfoComparer.Singleton);
IRandomSource rng = RandomDefaults.CreateRandomSource(0);
neatPop.InitialiseSpecies(speciationStrategy, 3, genomeComparerDescending, rng);
}
/// <summary>
/// Create and return a NeatEvolutionAlgorithm object ready for running the NEAT algorithm/search. Various sub-parts
/// of the algorithm are also constructed and connected up.
/// This overload accepts a pre-built genome population and their associated/parent genome factory.
/// </summary>
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList)
{
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric, _parallelOptions);
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationStrategy = ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
// Create the evolution algorithm.
NeatEvolutionAlgorithm <NeatGenome> ea = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy, complexityRegulationStrategy);
// Create IBlackBox evaluator.
DoublePoleBalancingEvaluator evaluator;
switch (_variantStr)
{
case "DoublePole":
evaluator = new DoublePoleBalancingEvaluator();
break;
case "DoublePoleNv":
evaluator = new DoublePoleBalancingEvaluatorNv();
break;
case "DoublePoleNvAntiWiggle":
evaluator = new DoublePoleBalancingEvaluatorNvAntiWiggle();
break;
default:
throw new SharpNeatException(string.Format("DoublePoleBalancing experiment config XML specifies unknown variant [{0}]", _variantStr));
}
// Create genome decoder.
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = CreateGenomeDecoder();
// Create a genome list evaluator. This packages up the genome decoder with the genome evaluator.
IGenomeListEvaluator <NeatGenome> innerEvaluator = new ParallelGenomeListEvaluator <NeatGenome, IBlackBox>(genomeDecoder, evaluator, _parallelOptions);
// Wrap the list evaluator in a 'selective' evaulator that will only evaluate new genomes. That is, we skip re-evaluating any genomes
// that were in the population in previous generations (elite genomes). This is determiend by examining each genome's evaluation info object.
IGenomeListEvaluator <NeatGenome> selectiveEvaluator = new SelectiveGenomeListEvaluator <NeatGenome>(
innerEvaluator,
SelectiveGenomeListEvaluator <NeatGenome> .CreatePredicate_OnceOnly());
// Initialize the evolution algorithm.
ea.Initialize(selectiveEvaluator, genomeFactory, genomeList);
// Finished. Return the evolution algorithm
return(ea);
}
private NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeListEvaluator <NeatGenome> evaluator, List <NeatGenome> list)
{
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy = new KMeansClusteringStrategy <NeatGenome>(distanceMetric);
IComplexityRegulationStrategy complexityRegulationStrategy = new DefaultComplexityRegulationStrategy(ComplexityCeilingType.Absolute, _complexityThreshold);
NeatEvolutionAlgorithm <NeatGenome> neatEvolutionAlgorithm = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy, complexityRegulationStrategy);
var genomeFactory = new NeatGenomeFactory(_inputCount.Value, _outputCount.Value, _neatGenomeParams);
neatEvolutionAlgorithm.Initialize(evaluator, genomeFactory, list);
return(neatEvolutionAlgorithm);
}
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList, IGenomeListEvaluator <NeatGenome> eval = null)
{
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric, _parallelOptions);
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationStrategy = new NullComplexityRegulationStrategy();// ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
// Create the evolution algorithm.
NeatEvolutionAlgorithm <NeatGenome> ea = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy, complexityRegulationStrategy);
// Create the MC evaluator
PasswordCrackingEvaluator.Passwords = _passwords;
// Create genome decoder.
IGenomeDecoder <NeatGenome, MarkovChain> genomeDecoder = CreateGenomeDecoder();
// If we're running specially on Condor, skip this
if (eval == null)
{
_evaluator = new PasswordCrackingEvaluator(_guesses, Hashed);
// Create a genome list evaluator. This packages up the genome decoder with the genome evaluator.
// IGenomeListEvaluator<NeatGenome> innerEvaluator = new ParallelGenomeListEvaluator<NeatGenome, MarkovChain>(genomeDecoder, _evaluator, _parallelOptions);
IGenomeListEvaluator <NeatGenome> innerEvaluator = new ParallelNEATGenomeListEvaluator <NeatGenome, MarkovChain>(genomeDecoder, _evaluator, this);
/*
* // Wrap the list evaluator in a 'selective' evaulator that will only evaluate new genomes. That is, we skip re-evaluating any genomes
* // that were in the population in previous generations (elite genomes). This is determiend by examining each genome's evaluation info object.
* IGenomeListEvaluator<NeatGenome> selectiveEvaluator = new SelectiveGenomeListEvaluator<NeatGenome>(
* innerEvaluator,
* SelectiveGenomeListEvaluator<NeatGenome>.CreatePredicate_OnceOnly());
*/
// Initialize the evolution algorithm.
ea.Initialize(innerEvaluator, genomeFactory, genomeList);
}
else
{
// Initialize the evolution algorithm.
ea.Initialize(eval, genomeFactory, genomeList);
}
// Finished. Return the evolution algorithm
return(ea);
}
private void Start()
{
int populationSize = 100;
NetworkActivationScheme activationScheme = NetworkActivationScheme.CreateAcyclicScheme();
NeatGenomeParameters neatParams = new NeatGenomeParameters();
neatParams.ActivationFn = TanH.__DefaultInstance;
neatParams.FeedforwardOnly = activationScheme.AcyclicNetwork;
IGenomeDecoder <NeatGenome, IBlackBox> neatDecoder = new NeatGenomeDecoder(activationScheme);
IGenomeFactory <NeatGenome> neatFactory = new NeatGenomeFactory(3, 3, neatParams);
List <NeatGenome> genomeList = neatFactory.CreateGenomeList(populationSize, 0);
ArenaEvaluator evaluator = GetComponent <ArenaEvaluator>();
evaluator.Initialize(neatDecoder);
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
// Evolution parameters
NeatEvolutionAlgorithmParameters neatEvolutionParams = new NeatEvolutionAlgorithmParameters();
neatEvolutionParams.SpecieCount = 10;
ISpeciationStrategy <NeatGenome> speciationStrategy = new KMeansClusteringStrategy <NeatGenome>(distanceMetric);
IComplexityRegulationStrategy complexityRegulationStrategy = new DefaultComplexityRegulationStrategy(ComplexityCeilingType.Absolute, 10);
NeatEvolutionAlgorithm <NeatGenome> ea = GetComponent <UnityEvolutionAlgorithm>();
ea.Construct(neatEvolutionParams, speciationStrategy, complexityRegulationStrategy, new NullGenomeListEvaluator <NeatGenome, IBlackBox>());
ea.Initialize(evaluator, neatFactory, genomeList);
ea.UpdateScheme = new UpdateScheme(1); // This needs to be set AFTER Initialize is called
ea.PausedEvent += (sender, e) =>
{
//ea.StartContinue();
};
ea.GenerationEvent += (sender, gen) =>
{
Debug.Log($"Generation {gen}");
Debug.Log($"Highest fitness: {ea.CurrentChampGenome.EvaluationInfo.Fitness}");
nnMesh.GenerateMesh(ea.CurrentChampGenome);
ea.RequestPause();
StartCoroutine(PauseRoutine(ea));
};
ea.StartContinue();
}
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList)
{
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy = new KMeansClusteringStrategy <NeatGenome>(distanceMetric);
IComplexityRegulationStrategy complexityRegulationStrategy = ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
BraidNeatEvolutionAlgorithm <NeatGenome> ea = new BraidNeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy, complexityRegulationStrategy);
// Create black box evaluator
BraidEvaluator evaluator = new BraidEvaluator(m_optimizer);
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = CreateGenomeDecoder();
IGenomeListEvaluator <NeatGenome> innerEvaluator = new BraidListEvaluator <NeatGenome, IBlackBox>(genomeDecoder, evaluator, m_optimizer);
ea.Initialize(innerEvaluator, genomeFactory, genomeList);
return(ea);
}
/// <summary>
/// Configures and instantiates the initialization evolutionary algorithm.
/// </summary>
/// <param name="parallelOptions">Synchronous/Asynchronous execution settings.</param>
/// <param name="genomeList">The initial population of genomes.</param>
/// <param name="genomeDecoder">The decoder to translate genomes into phenotypes.</param>
/// <param name="startingEvaluations">
/// The number of evaluations that preceeded this from which this process will pick up
/// (this is used in the case where we're restarting a run because it failed to find a solution in the allotted time).
/// </param>
protected void InitializeAlgorithm(ParallelOptions parallelOptions, List <NeatGenome> genomeList,
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder, ulong startingEvaluations)
{
ParallelOptions = parallelOptions;
InitialPopulation = genomeList;
StartingEvaluations = startingEvaluations;
GenomeDecoder = genomeDecoder;
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
SpeciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric, parallelOptions);
// Create complexity regulation strategy.
ComplexityRegulationStrategy =
ExperimentUtils.CreateComplexityRegulationStrategy(ComplexityRegulationStrategyDefinition,
ComplexityThreshold);
}
/// <summary>
/// Create and return a NeatEvolutionAlgorithm object ready for running the NEAT algorithm/search. Various sub-parts
/// of the algorithm are also constructed and connected up.
/// This overload accepts a pre-built genome2 population and their associated/parent genome2 factory.
/// </summary>
public NeatEvolutionAlgorithm <NeatGenome>[] CreateEvolutionAlgorithms(IGenomeFactory <NeatGenome> genomeFactory1, List <NeatGenome> genomeList1,
IGenomeFactory <NeatGenome> genomeFactory2, List <NeatGenome> genomeList2)
{
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric1 = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy1 = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric1, _parallelOptions);
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric2 = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy2 = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric2, _parallelOptions);
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationStrategy1 = ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationStrategy2 = ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
// Create the evolution algorithm.
NeatEvolutionAlgorithm <NeatGenome> ea1 = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy1, complexityRegulationStrategy1);
NeatEvolutionAlgorithm <NeatGenome> ea2 = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy2, complexityRegulationStrategy2);
// Create genome decoder.
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder1 = CreateGenomeDecoder();
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder2 = CreateGenomeDecoder();
// Create phenome evaluators. Note we are evolving one population of X players and one of O players.
ICoevolutionPhenomeEvaluator <IBlackBox> phenomeEvaluator1 = new TicTacToeHostParasiteEvaluator(SquareTypes.X);
ICoevolutionPhenomeEvaluator <IBlackBox> phenomeEvaluator2 = new TicTacToeHostParasiteEvaluator(SquareTypes.O);
// Create a genome list evaluator. This packages up the genome decoder with the phenome evaluator.
HostParasiteCoevolutionListEvaluator <NeatGenome, IBlackBox> genomeListEvaluator1 = new HostParasiteCoevolutionListEvaluator <NeatGenome, IBlackBox>(_parasiteCount, _championCount, ea2, genomeDecoder1, phenomeEvaluator1);
HostParasiteCoevolutionListEvaluator <NeatGenome, IBlackBox> genomeListEvaluator2 = new HostParasiteCoevolutionListEvaluator <NeatGenome, IBlackBox>(_parasiteCount, _championCount, ea1, genomeDecoder2, phenomeEvaluator2);
// Initialize the evolution algorithms.
ea1.Initialize(genomeListEvaluator1, genomeFactory1, genomeList1);
ea2.Initialize(genomeListEvaluator2, genomeFactory2, genomeList2);
// Set the evolution algorithms to update every generation.
ea1.UpdateScheme = new UpdateScheme(1);
ea2.UpdateScheme = new UpdateScheme(1);
// Finished. Return the evolution algorithms
return(new [] { ea1, ea2 });
}
/// <summary>
/// Create and return a NeatEvolutionAlgorithm object ready for running the NEAT algorithm/search. Various sub-parts
/// of the algorithm are also constructed and connected up.
/// This overload accepts a pre-built genome2 population and their associated/parent genome2 factory.
/// </summary>
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList)
{
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric, new ParallelOptions());
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationStrategy = ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
// Create the evolution algorithm.
NeatEvolutionAlgorithm <NeatGenome> ea = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy, complexityRegulationStrategy);
// Create genome decoder.
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = CreateGenomeDecoder();
// Finished. Return the evolution algorithm
return(ea);
}
private static ISpeciationStrategy <NeatGenome <double>, double> CreateSpeciationStrategy(
INeatExperiment <double> neatExperiment)
{
// Resolve a degreeOfParallelism (-1 is allowed in config, but must be resolved here to an actual degree).
int degreeOfParallelismResolved = ResolveDegreeOfParallelism(neatExperiment);
// Define a distance metric to use for k-means speciation; this is the default from sharpneat 2.x.
IDistanceMetric <double> distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
// Use k-means speciation strategy; this is the default from sharpneat 2.x.
// Create a serial (single threaded) strategy if degreeOfParallelism is one.
if (degreeOfParallelismResolved == 1)
{
return(new Neat.Speciation.GeneticKMeans.GeneticKMeansSpeciationStrategy <double>(distanceMetric, 5));
}
// Create a parallel (multi-threaded) strategy for degreeOfParallelism > 1.
return(new Neat.Speciation.GeneticKMeans.Parallelized.GeneticKMeansSpeciationStrategy <double>(distanceMetric, 5, degreeOfParallelismResolved));
}
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(
IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList)
{
// Create distance metric. Mismatched genes have a fixed distance of 10;
// for matched genes the distance is their weight difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy =
new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric);
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationStrategy = new NullComplexityRegulationStrategy();
// Create the evolution algorithm.
NeatEvolutionAlgorithm <NeatGenome> ea =
new NeatEvolutionAlgorithm <NeatGenome>(this.eaParams, speciationStrategy, complexityRegulationStrategy);
// Create genome decoder.
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = this.CreateGenomeDecoder();
var evaluator = new Evaluator();
// Create a genome list evaluator. This packages up the genome decoder with the genome evaluator.
//IGenomeListEvaluator<NeatGenome> innerEvaluator =
// new SerialGenomeListEvaluator<NeatGenome, IBlackBox>(genomeDecoder, evaluator);
IGenomeListEvaluator <NeatGenome> innerEvaluator =
new ParallelGenomeListEvaluator <NeatGenome, IBlackBox>(genomeDecoder, evaluator);
// Wrap the list evaluator in a 'selective' evaluator that will only evaluate new genomes.
// That is, we skip re-evaluating any genomes that were in the population in previous
// generations (elite genomes). This is determined by examining each genome's evaluation info object.
IGenomeListEvaluator <NeatGenome> selectiveEvaluator =
new SelectiveGenomeListEvaluator <NeatGenome>(
innerEvaluator,
SelectiveGenomeListEvaluator <NeatGenome> .CreatePredicate_OnceOnly());
// Initialize the evolution algorithm.
ea.Initialize(selectiveEvaluator, genomeFactory, genomeList);
ea.UpdateScheme = new UpdateScheme(1);
// Finished. Return the evolution algorithm
return(ea);
}
/// <summary>
/// Create and return a NeatEvolutionAlgorithm object ready for running the NEAT algorithm/search. Various sub-parts
/// of the algorithm are also constructed and connected up.
/// This overload accepts a pre-built genome population and their associated/parent genome factory.
/// </summary>
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList)
{
Debug.Log("........CreateEvolutionAlgorithm: Setting parameters");
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy = new KMeansClusteringStrategy <NeatGenome>(distanceMetric);
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationStrategy = ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
Debug.Log("........CreateEvolutionAlgorithm: Creating ea");
// Create the evolution algorithm.
NeatEvolutionAlgorithm <NeatGenome> ea = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy, complexityRegulationStrategy);
Debug.Log("........CreateEvolutionAlgorithm: Creating evaluator");
// Create IBlackBox evaluator.
CPPNRepairEvaluator2 evaluator = new CPPNRepairEvaluator2(this);
evaluator.SetOriginalFeatures(_originalFeatures);
Debug.Log("........CreateEvolutionAlgorithm: Creating genome decoder and serial evaluator");
// Create genome decoder.
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = CreateGenomeDecoder();
// Create a genome list evaluator. This packages up the genome decoder with the genome evaluator.
IGenomeListEvaluator <NeatGenome> innerEvaluator = new SerialGenomeListEvaluator <NeatGenome, IBlackBox>(genomeDecoder, evaluator);
// Wrap the list evaluator in a 'selective' evaulator that will only evaluate new genomes. That is, we skip re-evaluating any genomes
// that were in the population in previous generations (elite genomes). This is determiend by examining each genome's evaluation info object.
/*IGenomeListEvaluator<NeatGenome> selectiveEvaluator = new SelectiveGenomeListEvaluator<NeatGenome>(
* innerEvaluator,
* SelectiveGenomeListEvaluator<NeatGenome>.CreatePredicate_OnceOnly());
*/
// Initialize the evolution algorithm.
Debug.Log("........CreateEvolutionAlgorithm: Initializing ea");
ea.Initialize(innerEvaluator, genomeFactory, genomeList);
Debug.Log("........CreateEvolutionAlgorithm: Returning");
// Finished. Return the evolution algorithm
return(ea);
}
/*
* List<NeatGenome> CreateNewGenome(IGenomeFactory<NeatGenome> genomeFactory)
* {
* Console.WriteLine("Saved genome not found, creating new files.");
* return genomeFactory.CreateGenomeList(_populationSize, 0);
* }
*/
/// <summary>
/// Creates and returns a NeatEvolutionAlgorithm object ready for running
/// the NEAT algorithm/search. Various sub-parts of the algorithm are also
/// constructed and connected up. This overload accepts a pre-built genome2
/// population and their associated/parent genome2 factory.
/// </summary>
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(
IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList)
{
// Creates distance metric. Mismatched genes have a fixed distance of 10;
// for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
//ISpeciationStrategy<NeatGenome> speciationStrategy = new KMeansClusteringStrategy<NeatGenome>(distanceMetric);
ISpeciationStrategy <NeatGenome> speciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric, _parallelOptions);
IComplexityRegulationStrategy complexityRegulationStrategy =
ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
// Creates the evolution algorithm.
NeatEvolutionAlgorithm <NeatGenome> evolAlgorithm = new NeatEvolutionAlgorithm <NeatGenome>(
_eaParams, speciationStrategy, complexityRegulationStrategy, userName);
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = new NeatGenomeDecoder(_activationScheme);
// Creates a genome2 list evaluator. This packages up the genome2 decoder with the genome2 evaluator.
IGenomeListEvaluator <NeatGenome> genomeListEvaluator =
new ParallelGenomeListEvaluator <NeatGenome, IBlackBox>(genomeDecoder, PhenomeEvaluator, _parallelOptions);
//To use single-thread evaluator:
//IGenomeListEvaluator<NeatGenome> genomeListEvaluator =
// new SerialGenomeListEvaluator<NeatGenome, IBlackBox>(genomeDecoder, PhenomeEvaluator, false);
// Wraps the list evaluator in a 'selective' evaulator that will only
// evaluate new genomes. That is, we skip re-evaluating any genomes
// that were in the population in previous generations (elite genomes).
// This is determiend by examining each genome's evaluation info object.
/*
* int reevaluationPeriod = 1;
* genomeListEvaluator = new SelectiveGenomeListEvaluator<NeatGenome>(
* genomeListEvaluator,
* SelectiveGenomeListEvaluator<NeatGenome>.CreatePredicate_PeriodicReevaluation(reevaluationPeriod));
*/
genomeListEvaluator = new SelectiveGenomeListEvaluator <NeatGenome>(
genomeListEvaluator,
SelectiveGenomeListEvaluator <NeatGenome> .CreatePredicate_OnceOnly());
// Initializes the evolution algorithm.
evolAlgorithm.Initialize(genomeListEvaluator, genomeFactory, genomeList);
// Finished. Return the evolution algorithm
return(evolAlgorithm);
}
/// <summary>
/// Create and return a NeatEvolutionAlgorithm object ready for running the NEAT algorithm/search. Various sub-parts
/// of the algorithm are also constructed and connected up.
/// This overload accepts a pre-built genome population and their associated/parent genome factory.
/// </summary>
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList)
{
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric, _parallelOptions);
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationStrategy = ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
// Create the evolution algorithm.
NeatEvolutionAlgorithm <NeatGenome> ea = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy, complexityRegulationStrategy);
// Create IBlackBox evaluator.
DeepBeliefNetworkBiasEvaluator evaluator = new DeepBeliefNetworkBiasEvaluator();
// Create genome decoder. Decodes to a neural network packaged with an activation scheme that defines a fixed number of activations per evaluation.
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = CreateGenomeDecoder(_lengthCppnInput);
// Create a genome list evaluator. This packages up the genome decoder with the genome evaluator.
IGenomeListEvaluator <NeatGenome> innerEvaluator = null;
if (Constants.IS_MULTI_THREADING)
{
innerEvaluator = new ParallelGenomeListEvaluator <NeatGenome, IBlackBox>(genomeDecoder, evaluator, _parallelOptions);
}
else
{
innerEvaluator = new SerialGenomeListEvaluator <NeatGenome, IBlackBox>(genomeDecoder, evaluator);
}
// Wrap the list evaluator in a 'selective' evaulator that will only evaluate new genomes. That is, we skip re-evaluating any genomes
// that were in the population in previous generations (elite genomes). This is determiend by examining each genome's evaluation info object.
IGenomeListEvaluator <NeatGenome> selectiveEvaluator = new SelectiveGenomeListEvaluator <NeatGenome>(
innerEvaluator,
SelectiveGenomeListEvaluator <NeatGenome> .CreatePredicate_OnceOnly());
// Initialize the evolution algorithm.
ea.Initialize(selectiveEvaluator, genomeFactory, genomeList);
// Finished. Return the evolution algorithm
return(ea);
}
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory <NeatGenome> genomeFactory,
List <NeatGenome> genomeList)
{
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy = new KMeansClusteringStrategy <NeatGenome>(distanceMetric);
IComplexityRegulationStrategy complexityRegulationStrategy =
ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
NeatEvolutionAlgorithm <NeatGenome> ea = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy,
complexityRegulationStrategy);
// Creates black box evaluator
SimpleEvaluator evaluator = new SimpleEvaluator(_optimizer);
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = CreateGenomeDecoder();
IGenomeListEvaluator <NeatGenome> innerEvaluator = new UnityParallelListEvaluator <NeatGenome, IBlackBox>(
genomeDecoder, evaluator, _optimizer);
IGenomeListEvaluator <NeatGenome> selectiveEvaluator = new SelectiveGenomeListEvaluator <NeatGenome>(
innerEvaluator, SelectiveGenomeListEvaluator <NeatGenome> .CreatePredicate_OnceOnly());
ea.Initialize(innerEvaluator, genomeFactory, genomeList);
return(ea);
}
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList)
{
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy =
new KMeansClusteringStrategy <NeatGenome>(distanceMetric);
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationStrategy =
ExperimentUtils.CreateComplexityRegulationStrategy("absolute", 10);
// Create the evolution algorithm.
var ea = new NeatEvolutionAlgorithm <NeatGenome>(
NeatEvolutionAlgorithmParameters,
speciationStrategy,
complexityRegulationStrategy);
// Create IBlackBox evaluator.
// var evaluator = new RemoteXorEvaluator();
var evaluator = new RemoteBatchXorEvaluator();
//LocalXorEvaluator evaluator = new LocalXorEvaluator();
// Create genome decoder.
IGenomeDecoder <NeatGenome, FastCyclicNetwork> genomeDecoder = _decoder;
// Create a genome list evaluator. This packages up the genome decoder with the genome evaluator.
IGenomeListEvaluator <NeatGenome> innerEvaluator = new BatchGenomeListEvaluator <NeatGenome, FastCyclicNetwork>(genomeDecoder, evaluator);
// Wrap the list evaluator in a 'selective' evaulator that will only evaluate new genomes. That is, we skip re-evaluating any genomes
// that were in the population in previous generations (elite genomes). This is determined by examining each genome's evaluation info object.
IGenomeListEvaluator <NeatGenome> selectiveEvaluator = new SelectiveGenomeListEvaluator <NeatGenome>(
innerEvaluator,
SelectiveGenomeListEvaluator <NeatGenome> .CreatePredicate_OnceOnly());
// Initialize the evolution algorithm.
ea.Initialize(selectiveEvaluator, genomeFactory, genomeList);
// Finished. Return the evolution algorithm
return(ea);
}
/// <summary>
/// Create and return a NeatEvolutionAlgorithm object ready for running the NEAT algorithm/search. Various sub-parts
/// of the algorithm are also constructed and connected up.
/// This overload accepts a pre-built genome2 population and their associated/parent genome2 factory.
/// </summary>
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList)
{
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric, new ParallelOptions());
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationStrategy = new NullComplexityRegulationStrategy();// ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
// Create the evolution algorithm.
NeatEvolutionAlgorithm <NeatGenome> ea = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy, complexityRegulationStrategy);
// Create genome decoder.
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = CreateGenomeDecoder();
// Create a genome list evaluator. This packages up the genome decoder with the phenome evaluator.
_evaluator = new ForagingEvaluator <NeatGenome>(genomeDecoder, _world, _agentType, _navigationEnabled, _hidingEnabled)
{
MaxTimeSteps = _timeStepsPerGeneration,
EvoParadigm = _paradigm,
MemParadigm = _memory,
GenerationsPerMemorySize = _memGens,
MaxMemorySize = _maxMemorySize,
TeachParadigm = _teaching,
TrialId = TrialId,
PredatorCount = _predCount,
PredatorDistribution = PredatorDistribution,
PredatorTypes = _predTypes,
PredatorGenerations = _predGens,
DistinguishPredators = _distinguishPreds,
LogDiversity = _logDiversity
};
// Initialize the evolution algorithm.
ea.Initialize(_evaluator, genomeFactory, genomeList);
// Finished. Return the evolution algorithm
return(ea);
}
/// <summary>
/// Create and return a NeatEvolutionAlgorithm object ready for running the NEAT algorithm/search. Various sub-parts
/// of the algorithm are also constructed and connected up.
/// This overload accepts a pre-built genome population and their associated/parent genome factory.
/// </summary>
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList)
{
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weigth difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric, _parallelOptions);
// Create the evolution algorithm.
NeatEvolutionAlgorithm <NeatGenome> ea = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy, _complexityRegulationStrategy);
// Create genome decoder.
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = CreateGenomeDecoder();
INoveltyScorer <NeatGenome> noveltyScorer = new TuringNoveltyScorer <NeatGenome>(_noveltySearchParams);
IGeneticDiversityScorer <NeatGenome> geneticDiversityScorer = new GeneticDiversityKnn <NeatGenome>(_neatGenomeParams.ConnectionWeightRange);
IMultiObjectiveScorer multiObjectiveScorer = new NSGAII(_multiObjectiveParams);
_listEvaluator = new MultiObjectiveListEvaluator <NeatGenome, IBlackBox>(
genomeDecoder,
_evaluator,
noveltyScorer,
geneticDiversityScorer,
multiObjectiveScorer,
_multiThreading,
_parallelOptions);
_listEvaluator.MultiObjectiveParams = _multiObjectiveParams;
_listEvaluator.ReportInterval = _logInterval;
NoveltySearchEnabled = _noveltySearchParams?.Enabled ?? false;
MultiObjectiveEnabled = _multiObjectiveParams?.Enabled ?? false;
// Initialize the evolution algorithm.
ea.Initialize(_listEvaluator, genomeFactory, genomeList);
ea.UpdateScheme = new UpdateScheme(1);
// Finished. Return the evolution algorithm
return(ea);
}
private static void Train()
{
File.WriteAllText($"{NeatConsts.experimentName}/fitness.csv", "generation,firness\n");
var neatGenomeFactory = new NeatGenomeFactory(NeatConsts.ViewX * NeatConsts.ViewY * NeatConsts.typeIds.Count, 1);
var genomeList = neatGenomeFactory.CreateGenomeList(NeatConsts.SpecCount, 0);
var eaParams = new NeatEvolutionAlgorithmParameters
{
SpecieCount = NeatConsts.SpecCount
};
//var distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
var distanceMetric = new ManhattanDistanceMetric();
var parallelOptions = new ParallelOptions();
var speciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric, parallelOptions);
//var speciationStrategy = new KMeansClusteringStrategy<NeatGenome>(distanceMetric);
//var speciationStrategy = new RandomClusteringStrategy<NeatGenome>();
var complexityRegulationStrategy = new NullComplexityRegulationStrategy();
//var complexityRegulationStrategy = new DefaultComplexityRegulationStrategy(ComplexityCeilingType.Relative, 0.50);
var ea = new NeatEvolutionAlgorithm <NeatGenome>(eaParams, speciationStrategy, complexityRegulationStrategy);
var activationScheme = NetworkActivationScheme.CreateCyclicFixedTimestepsScheme(1);
var genomeDecoder = new NeatGenomeDecoder(activationScheme);
var phenomeEvaluator = new GameEvaluator();
var genomeListEvaluator = new ParallelGenomeListEvaluator <NeatGenome, IBlackBox>(genomeDecoder, phenomeEvaluator, parallelOptions);
ea.Initialize(genomeListEvaluator, neatGenomeFactory, genomeList);
ea.UpdateScheme = new UpdateScheme(NeatConsts.LogRate);
ea.StartContinue();
ea.UpdateEvent += Ea_UpdateEvent;
while (ea.RunState != RunState.Paused)
{
}
ea.Stop();
}
/// <summary>
/// Create and return a NeatEvolutionAlgorithm object ready for running the NEAT algorithm/search. Various sub-parts
/// of the algorithm are also constructed and connected up.
/// This overload accepts a pre-built genome population and their associated/parent genome factory.
/// </summary>
public NeatEvolutionAlgorithm <NeatGenome> CreateEvolutionAlgorithm(IGenomeFactory <NeatGenome> genomeFactory, List <NeatGenome> genomeList)
{
// Create distance metric. Mismatched genes have a fixed distance of 10; for matched genes the distance is their weight difference.
IDistanceMetric distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
ISpeciationStrategy <NeatGenome> speciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric, _parallelOptions);
// Create complexity regulation strategy.
IComplexityRegulationStrategy complexityRegulationStrategy = ExperimentUtils.CreateComplexityRegulationStrategy(_complexityRegulationStr, _complexityThreshold);
// Create the evolution algorithm.
NeatEvolutionAlgorithm <NeatGenome> ea = new NeatEvolutionAlgorithm <NeatGenome>(_eaParams, speciationStrategy, complexityRegulationStrategy);
// Create genome decoder.
IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = CreateGenomeDecoder();
// All-encompassing info object
_info = new Info(this, ea, genomeDecoder);
// Create IBlackBox evaluator.
IPDEvaluator evaluator = new IPDEvaluator(ref _info);
// Create a genome list evaluator. This packages up the genome decoder with the genome evaluator.
IGenomeListEvaluator <NeatGenome> innerEvaluator = new ParallelGenomeListEvaluator <NeatGenome, IBlackBox>(genomeDecoder, evaluator, _parallelOptions);
// Wrap the list evaluator in a 'selective' evaluator that will only evaluate new genomes. That is, we skip re-evaluating any genomes
// that were in the population in previous generations (elite genomes). This is determined by examining each genome's evaluation info object.
IGenomeListEvaluator <NeatGenome> selectiveEvaluator = new SelectiveGenomeListEvaluator <NeatGenome>(
innerEvaluator,
SelectiveGenomeListEvaluator <NeatGenome> .CreatePredicate_OnceOnly());
// Initialize the evolution algorithm.
ea.Initialize(selectiveEvaluator, genomeFactory, genomeList);
// Finished. Return the evolution algorithm
return(ea);
}
public NeatEvolutionAlgorithm <double> CreateNeatEvolutionAlgorithm()
{
// Create a genome evaluator.
var genomeListEvaluator = CreateGenomeListEvaluator(out int inputCount, out int outputCount);
// Create an initial population.
_metaNeatGenome = CreateMetaNeatGenome(inputCount, outputCount);
_eaSettings = new NeatEvolutionAlgorithmSettings();
_eaSettings.SpeciesCount = 40;
_neatPop = CreatePopulation(_metaNeatGenome, 600);
// Create a speciation strategy instance.
var distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
var speciationStrategy = new SharpNeat.Neat.Speciation.GeneticKMeans.Parallelized.GeneticKMeansSpeciationStrategy <double>(distanceMetric, 5);
// Create an asexual reproduction settings object (default settings).
var reproductionAsexualSettings = new NeatReproductionAsexualSettings();
// Create a sexual reproduction settings object (default settings).
var reproductionSexualSettings = new NeatReproductionSexualSettings();
// Create a connection weight mutation scheme.
var weightMutationScheme = WeightMutationSchemeFactory.CreateDefaultScheme(_metaNeatGenome.ConnectionWeightScale);
// Pull all of the parts together into an evolution algorithm instance.
var ea = new NeatEvolutionAlgorithm <double>(
_eaSettings,
genomeListEvaluator,
speciationStrategy,
_neatPop,
reproductionAsexualSettings,
reproductionSexualSettings,
weightMutationScheme);
return(ea);
}
public void TestSingleMatchGenomes()
{
var connGenes1 = new ConnectionGenes <double>(5);
connGenes1[0] = (0, 10, 1.0);
connGenes1[1] = (1, 11, 2.0);
connGenes1[2] = (2, 12, 3.0);
connGenes1[3] = (3, 13, 4.0);
connGenes1[4] = (4, 14, 5.0);
var connGenes2 = new ConnectionGenes <double>(1);
connGenes2[0] = (4, 14, 20.0);
var distanceMetric = new ManhattanDistanceMetric();
// GetDistance() tests.
Assert.Equal(25, distanceMetric.CalcDistance(connGenes1, connGenes2));
Assert.Equal(25, distanceMetric.CalcDistance(connGenes2, connGenes1));
// TestDistance() tests.
Assert.True(distanceMetric.TestDistance(connGenes1, connGenes2, 25 + 0.001));
Assert.False(distanceMetric.TestDistance(connGenes1, connGenes2, 25 - 0.001));
}
public static void Main(string[] args)
{
var random = new Random();
var circuits = circuitsFilePaths().ToArray();
var perceptionStep = TimeSpan.FromSeconds(0.1);
var simulationStep = TimeSpan.FromSeconds(0.05); // 20Hz
var maximumSimulationTime = TimeSpan.FromSeconds(60);
var tracks = circuits.Select(circuitPath => Track.Load($"{circuitPath}/circuit_definition.json"));
var worlds = tracks.Select(track => new StandardWorld(track, simulationStep)).ToArray();
var inputSamplesCount = 3;
var maximumScanningDistance = 200;
ILidar createLidarFor(ITrack track)
=> new Lidar(track, inputSamplesCount, Angle.FromDegrees(135), maximumScanningDistance);
var settings = new EvolutionSettings
{
PopulationSize = 1000,
SpeciesCount = 30,
ElitismProportion = 0,
ComplexityThreshold = 50
};
// prepare simulation
var parameters = new NeatEvolutionAlgorithmParameters
{
ElitismProportion = settings.ElitismProportion,
SpecieCount = settings.SpeciesCount
};
var distanceMetric = new ManhattanDistanceMetric(1.0, 0.0, 10.0);
var parallelOptions = new ParallelOptions {
MaxDegreeOfParallelism = 4
};
var speciationStrategy = new ParallelKMeansClusteringStrategy <NeatGenome>(distanceMetric, parallelOptions);
var complexityRegulationStrategy = new DefaultComplexityRegulationStrategy(ComplexityCeilingType.Absolute, settings.ComplexityThreshold);
var evolutionaryAlgorithm = new NeatEvolutionAlgorithm <NeatGenome>(
parameters,
speciationStrategy,
complexityRegulationStrategy);
var phenomeEvaluator = new RaceSimulationEvaluator(
random,
simulationStep,
perceptionStep,
maximumSimulationTime,
worlds,
createLidarFor);
var genomeDecoder = new NeatGenomeDecoder(NetworkActivationScheme.CreateAcyclicScheme());
var genomeListEvaluator = new ParallelGenomeListEvaluator <NeatGenome, IBlackBox>(
genomeDecoder,
phenomeEvaluator);
evolutionaryAlgorithm.Initialize(
genomeListEvaluator,
genomeFactory: new NeatGenomeFactory(
inputNeuronCount: inputSamplesCount,
outputNeuronCount: 2,
DefaultActivationFunctionLibrary.CreateLibraryNeat(new BipolarSigmoid()),
new NeatGenomeParameters
{
FeedforwardOnly = true,
AddNodeMutationProbability = 0.03,
DeleteConnectionMutationProbability = 0.05,
ConnectionWeightMutationProbability = 0.08,
FitnessHistoryLength = 10,
}),
settings.PopulationSize);
var lastVisualization = DateTimeOffset.Now;
evolutionaryAlgorithm.UpdateEvent += onUpdate;
evolutionaryAlgorithm.StartContinue();
Console.WriteLine("Press enter to stop the evolution.");
Console.ReadLine();
Console.WriteLine("Finishing the evolution.");
evolutionaryAlgorithm.Stop();
Console.WriteLine("Evolution is stopped.");
// simulate best individual
Console.WriteLine("Simulating best individual...");
evaluate(evolutionaryAlgorithm.CurrentChampGenome);
Console.WriteLine("Done.");
void onUpdate(object sender, EventArgs e)
{
Console.WriteLine($"Generation #{evolutionaryAlgorithm.CurrentGeneration}");
Console.WriteLine($"- max fitness: {evolutionaryAlgorithm.Statistics._maxFitness}");
Console.WriteLine($"- mean fitness: {evolutionaryAlgorithm.Statistics._meanFitness}");
Console.WriteLine();
if (DateTimeOffset.Now - lastVisualization > TimeSpan.FromSeconds(35))
{
lastVisualization = DateTimeOffset.Now;
Console.WriteLine("Simulating currently best individual...");
evaluate(evolutionaryAlgorithm.CurrentChampGenome);
}
}
void evaluate(NeatGenome genome)
{
var worldId = random.Next(0, worlds.Length - 1);
var world = worlds[worldId];
var bestIndividual = genomeDecoder.Decode(genome);
var agent = new NeuralNetworkAgent(createLidarFor(world.Track), bestIndividual);
var simulation = new Simulation.Simulation(agent, world);
var summary = simulation.Simulate(simulationStep, perceptionStep, maximumSimulationTime);
File.Copy($"{circuits[worldId]}/visualization.svg", "C:/Users/simon/Projects/racer-experiment/simulator/src/visualization.svg", overwrite: true);
IO.Simulation.StoreResult(world.Track, world.VehicleModel, summary, "", "C:/Users/simon/Projects/racer-experiment/simulator/src/report.json");
}
}