EvolutionManager()
{
//generic neat params, if need to change, just create a function that swaps them in
neatParams = new NeatParameters();
//neatParams.noveltySearch = true;
//neatParams.noveltyFloat = true;
neatParams.multiobjective = true;
neatParams.archiveThreshold = 0.5;
//neatParams.archiveThreshold = 300000.0;
//maybe we load this idgenerator from server or local database, just keep that in mind
idgen = new IdGenerator();
//we just default to this, but it doesn't have to be so
this.setDefaultCPPNs(4, 3);
genomeListDictionary.Add(CurrentGenomePool, new GenomeList());
}
//private static Random random;
public static void Main(string[] args)
{
Util.Initialize(args[0]);
var idgen = new IdGenerator();
IExperiment experiment = new LimitExperiment();
XmlSerializer ser = new XmlSerializer(typeof(Settings));
//Settings settings = new Settings()
//{
// SmallBlind = 1,
// BigBlind = 2,
// GamesPerIndividual = 100,
// LogFile = "mutlithreaded_log.txt",
// MaxHandsPerTourney = 200,
// PlayersPerGame = 6,
// StackSize = 124,
// Threads = 4
//};
//ser.Serialize(new StreamWriter("settings.xml"), settings);
Settings settings = (Settings)ser.Deserialize(new StreamReader("settings.xml"));
var eval = new PokerPopulationEvaluator<SimpleLimitNeuralNetPlayer2, RingGamePlayerEvaluator>(settings);
var ea = new EvolutionAlgorithm(
new Population(idgen,
GenomeFactory.CreateGenomeList(experiment.DefaultNeatParameters,
idgen, experiment.InputNeuronCount,
experiment.OutputNeuronCount,
experiment.DefaultNeatParameters.pInitialPopulationInterconnections,
experiment.DefaultNeatParameters.populationSize)),
eval,
experiment.DefaultNeatParameters);
Console.WriteLine("Starting real evolution");
for (int i = 0; true; i++)
{
Console.WriteLine("Generation {0}", i + 1);
ea.PerformOneGeneration();
Console.WriteLine("Champion Fitness={0}", ea.BestGenome.Fitness);
var doc = new XmlDocument();
XmlGenomeWriterStatic.Write(doc, (NeatGenome)ea.BestGenome);
FileInfo oFileInfo = new FileInfo("genomes_simple\\" + "bestGenome" + i.ToString() + ".xml");
doc.Save(oFileInfo.FullName);
}
}
public static GenomeList CreateGenomeListPreserveIDs(GenomeList seedGenomes, int length, NeatParameters neatParameters, IdGenerator idGenerator, AssessGenotypeFunction assess)
{
//Eventually, WIN will be brought in to maintain the genomes, for now, no need
//Build the list.
GenomeList genomeList = new GenomeList();
if (length < seedGenomes.Count)
throw new Exception("Attempting to generate a population that is smaller than the number of seeds (i.e. some seeds will be lost). Please change pop size to accomodate for all seeds.");
NeatGenome newGenome;
for (int i = 0; i < seedGenomes.Count; i++)
{
// Use each seed directly just once.
newGenome = new NeatGenome((NeatGenome)seedGenomes[i], idGenerator.NextGenomeId);
genomeList.Add(newGenome);
}
int testCount = 0; int maxTests = 5;
// For the remainder we alter the weights.
//for (int i = 1; i < length; i++)
//{
while (genomeList.Count < length)
{
newGenome = new NeatGenome((NeatGenome)seedGenomes[Utilities.Next(seedGenomes.Count)], idGenerator.NextGenomeId);
// Reset the connection weights
//in this particular instance, we would take a snapshot of the genome AFTER mutation for WIN purposes. But we don't track genomes yet
foreach (ConnectionGene connectionGene in newGenome.ConnectionGeneList)
connectionGene.Weight += (0.1 - Utilities.NextDouble() * 0.2);
//!connectionGene.Weight = (Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange/2.0;
//Console.WriteLine((0.1 - Utilities.NextDouble() * 0.2));
//newGenome.ConnectionGeneList.Add(new ConnectionGene(idGenerator.NextInnovationId,5,newGenome.NeuronGeneList[Utilities.Next(newGenome.NeuronGeneList.Count-7)+7].InnovationId ,(Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange/2.0));
//newGenome.ConnectionGeneList.Add(new ConnectionGene(idGenerator.NextInnovationId, 6, newGenome.NeuronGeneList[Utilities.Next(newGenome.NeuronGeneList.Count - 7) + 7].InnovationId, (Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange / 2.0));
//if we have an assess function, it should be used for generating this individual!
if (assess != null && assess(newGenome) && testCount++ < maxTests)
{
//after adding the genome, reset test count
genomeList.Add(newGenome);
testCount = 0;
}
else if (assess == null)
genomeList.Add(newGenome);
else if (testCount >= maxTests)
{
genomeList.Add(newGenome);
testCount = 0;
}
}
//
return genomeList;
}
public void initializeEvolution(int populationSize)
{
if (logOutput != null)
logOutput.Close();
logOutput = new StreamWriter(outputFolder + "logfile.txt");
IdGenerator idgen = new IdGenerator();
ea = new EvolutionAlgorithm(new Population(idgen, GenomeFactory.CreateGenomeList(neatParams, idgen, cppnInputs, cppnOutputs, neatParams.pInitialPopulationInterconnections, populationSize)), populationEval, neatParams);
}
/// <summary>
/// Create an IdGeneratoy by interrogating the provided population of Genomes.
/// This routine also fixes any duplicate IDs that are found in the
/// population.
/// </summary>
/// <param name="pop"></param>
/// <returns></returns>
public IdGenerator CreateIdGenerator(GenomeList genomeList)
{
uint maxGenomeId=0;
uint maxInnovationId=0;
// First pass: Determine the current maximum genomeId and innovationId.
foreach(NeatGenome genome in genomeList)
{
if(genome.GenomeId > maxGenomeId)
maxGenomeId = genome.GenomeId;
// Neuron IDs actualy come from the innovation IDs generator, so although they
// aren't used as historical markers we should count them as innovation IDs here.
foreach(NeuronGene neuronGene in genome.NeuronGeneList)
{
if(neuronGene.InnovationId > maxInnovationId)
maxInnovationId = neuronGene.InnovationId;
}
foreach(ConnectionGene connectionGene in genome.ConnectionGeneList)
{
if(connectionGene.InnovationId > maxInnovationId)
maxInnovationId = connectionGene.InnovationId;
}
}
if(maxGenomeId==uint.MaxValue)
{ //reset to zero.
maxGenomeId=0;
}
else
{ // Increment to next available ID.
maxGenomeId++;
}
if(maxInnovationId==uint.MaxValue)
{ //reset to zero.
maxInnovationId=0;
}
else
{ // Increment to next available ID.
maxInnovationId++;
}
// Create an IdGenerator using the discovered maximum IDs.
IdGenerator idGenerator = new IdGenerator(maxGenomeId, maxInnovationId);
// Second pass: Check for duplicate genome IDs.
Hashtable genomeIdTable = new Hashtable();
Hashtable innovationIdTable = new Hashtable();
foreach(NeatGenome genome in genomeList)
{
if(genomeIdTable.Contains(genome.GenomeId))
{ // Assign this genome a new Id.
genome.GenomeId = idGenerator.NextGenomeId;
}
//Register the ID.
genomeIdTable.Add(genome.GenomeId, null);
}
return idGenerator;
}
public Population(IdGenerator idGenerator, GenomeList genomeList)
{
this.idGenerator = idGenerator;
this.genomeList = genomeList;
this.populationSize = genomeList.Count;
}
public static GenomeList CreateGenomeList(Population seedPopulation, int length, NeatParameters neatParameters, IdGenerator idGenerator)
{
//Build the list.
GenomeList genomeList = new GenomeList();
int seedIdx=0;
for(int i=0; i<length; i++)
{
NeatGenome newGenome = new NeatGenome((NeatGenome)seedPopulation.GenomeList[seedIdx], idGenerator.NextGenomeId);
// Reset the connection weights
foreach(ConnectionGene connectionGene in newGenome.ConnectionGeneList)
connectionGene.Weight = (Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange/2.0;
genomeList.Add(newGenome);
if(++seedIdx >= seedPopulation.GenomeList.Count)
{ // Back to first genome.
seedIdx=0;
}
}
return genomeList;
}
public static GenomeList CreateGenomeListAddedInputs(NeatGenome seedGenome, int length, NeatParameters neatParameters, IdGenerator idGenerator)
{
//Build the list.
GenomeList genomeList = new GenomeList();
// Use the seed directly just once.
NeatGenome newGenome = new NeatGenome(seedGenome, idGenerator.NextGenomeId);
//genomeList.Add(newGenome);
// For the remainder we alter the weights.
for (int i = 0; i < length; i++)
{
newGenome = new NeatGenome(seedGenome, idGenerator.NextGenomeId);
// Reset the connection weights
foreach (ConnectionGene connectionGene in newGenome.ConnectionGeneList)
connectionGene.Weight = (Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange / 2.0;
newGenome.ConnectionGeneList.Add(new ConnectionGene(idGenerator.NextInnovationId, 5, newGenome.NeuronGeneList[Utilities.Next(newGenome.NeuronGeneList.Count - 7) + 7].InnovationId, (Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange / 2.0));
newGenome.ConnectionGeneList.Add(new ConnectionGene(idGenerator.NextInnovationId, 6, newGenome.NeuronGeneList[Utilities.Next(newGenome.NeuronGeneList.Count - 7) + 7].InnovationId, (Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange / 2.0));
genomeList.Add(newGenome);
}
//
return genomeList;
}
/// <summary>
/// Add a new node to the Genome. We do this by removing a connection at random and inserting
/// a new node and two new connections that make the same circuit as the original connection.
///
/// This way the new node is properly integrated into the network from the outset.
/// </summary>
/// <param name="ea"></param>
private void Mutate_AddNode(NeatParameters neatParameters, IdGenerator idGen, Hashtable NewNeuronGeneStructTable)
{
if(connectionGeneList.Count==0)
return;
// Select a connection at random.
int connectionToReplaceIdx = (int)Math.Floor(Utilities.NextDouble() * connectionGeneList.Count);
ConnectionGene connectionToReplace = connectionGeneList[connectionToReplaceIdx];
// Delete the existing connection. JOEL: Why delete old connection?
//connectionGeneList.RemoveAt(connectionToReplaceIdx);
// Check if this connection has already been split on another genome. If so then we should re-use the
// neuron ID and two connection ID's so that matching structures within the population maintain the same ID.
object existingNeuronGeneStruct = NewNeuronGeneStructTable[connectionToReplace.InnovationId];
NeuronGene newNeuronGene;
ConnectionGene newConnectionGene1;
ConnectionGene newConnectionGene2;
IActivationFunction actFunct;
WINManager win = WINManager.SharedWIN;
WINNode node;
WINConnection connection;
if(existingNeuronGeneStruct==null)
{ // No existing matching structure, so generate some new ID's.
//TODO: DAVID proper random activation function
// Replace connectionToReplace with two new connections and a neuron.
actFunct=ActivationFunctionFactory.GetRandomActivationFunction(neatParameters);
//newNeuronGene = new NeuronGene(ea.NextInnovationId, NeuronType.Hidden, actFunct);
//we should be making a call to WIN anytime we call for a new innovationID
//here we create a new node, and two new connections
//we don't send in a genomeID here, so we get it set for us!
node = win.createWINNode(new PropertyObject() { { WINNode.SNodeString, NeuronType.Hidden.ToString()}});
newNeuronGene = new NeuronGene(null, node.UniqueID, (neuronGeneList.GetNeuronById(connectionToReplace.SourceNeuronId).Layer + neuronGeneList.GetNeuronById(connectionToReplace.TargetNeuronId).Layer) / 2.0, NeuronType.Hidden, actFunct);
//we don't send in any uniqueIDs so they are generated for us, and we update our idGen object
connection = win.createWINConnection(WINConnection.ConnectionWithProperties(connectionToReplace.SourceNeuronId, newNeuronGene.InnovationId), idGen);
newConnectionGene1 = new ConnectionGene(connection.UniqueID, connection.SourceID, connection.TargetID , 1.0);
//we don't send in any uniqueIDs so they are generated for us, and we update our idGen object
connection = win.createWINConnection(WINConnection.ConnectionWithProperties(newNeuronGene.InnovationId, connectionToReplace.TargetNeuronId), idGen);
newConnectionGene2 = new ConnectionGene(connection.UniqueID, connection.SourceID, connection.TargetID, connectionToReplace.Weight);
// Register the new ID's with NewNeuronGeneStructTable.
NewNeuronGeneStructTable.Add(connectionToReplace.InnovationId,
new NewNeuronGeneStruct(newNeuronGene, newConnectionGene1, newConnectionGene2));
}
else
{ // An existing matching structure has been found. Re-use its ID's
//Since we don't call idGen.nextinnovationID, we don't have to create anything new
//however, we need to note the change in weights override previous weight values
//this should be documented in WIN - either explicitly (calling a function to note changes) or implicitly (by scanning the changes in a saved genome)
//Probably explicitly, calling a mutate function for a SingleStep (since we are in the SingleStep process of creating new individuals)
//TODO: DAVID proper random activation function
// Replace connectionToReplace with two new connections and a neuron.
actFunct = ActivationFunctionFactory.GetRandomActivationFunction(neatParameters);
NewNeuronGeneStruct tmpStruct = (NewNeuronGeneStruct)existingNeuronGeneStruct;
//newNeuronGene = new NeuronGene(tmpStruct.NewNeuronGene.InnovationId, NeuronType.Hidden, actFunct);
newNeuronGene = new NeuronGene(null, tmpStruct.NewNeuronGene.InnovationId, tmpStruct.NewNeuronGene.Layer, NeuronType.Hidden, actFunct);
newConnectionGene1 = new ConnectionGene(tmpStruct.NewConnectionGene_Input.InnovationId, connectionToReplace.SourceNeuronId, newNeuronGene.InnovationId, 1.0);
newConnectionGene2 = new ConnectionGene(tmpStruct.NewConnectionGene_Output.InnovationId, newNeuronGene.InnovationId, connectionToReplace.TargetNeuronId, connectionToReplace.Weight);
}
// Add the new genes to the genome.
neuronGeneList.Add(newNeuronGene);
connectionGeneList.InsertIntoPosition(newConnectionGene1);
connectionGeneList.InsertIntoPosition(newConnectionGene2);
}
private void Mutate_AddModule(NeatParameters neatParameters, IdGenerator idGen, Hashtable NewConnectionGeneTable)
{
// Find all potential inputs, or quit if there are not enough.
// Neurons cannot be inputs if they are dummy input nodes created for another module.
NeuronGeneList potentialInputs = new NeuronGeneList();
foreach (NeuronGene n in neuronGeneList) {
if (!(n.ActivationFunction is ModuleInputNeuron)) {
potentialInputs.Add(n);
}
}
if (potentialInputs.Count < 1)
return;
// Find all potential outputs, or quit if there are not enough.
// Neurons cannot be outputs if they are dummy input or output nodes created for another module, or network input or bias nodes.
NeuronGeneList potentialOutputs = new NeuronGeneList();
foreach (NeuronGene n in neuronGeneList) {
if (n.NeuronType != NeuronType.Bias && n.NeuronType != NeuronType.Input
&& !(n.ActivationFunction is ModuleInputNeuron)
&& !(n.ActivationFunction is ModuleOutputNeuron)) {
potentialOutputs.Add(n);
}
}
if (potentialOutputs.Count < 1)
return;
// Pick a new function for the new module.
IModule func = ModuleFactory.GetRandom();
WINManager win = WINManager.SharedWIN;
WINNode node;
WINConnection connection;
// Choose inputs uniformly at random, with replacement.
// Create dummy neurons to represent the module's inputs.
// Create connections between the input nodes and the dummy neurons.
IActivationFunction inputFunction = ActivationFunctionFactory.GetActivationFunction("ModuleInputNeuron");
List<long> inputDummies = new List<long>(func.InputCount);
for (int i = 0; i < func.InputCount; i++) {
//we are calling nextinnovationID, this is the place for WIN!
//in reality, win should know the activation function as well, but that's not currently implemented
//here we create a new node, and two new connections
//we don't send in a genomeID here, so we get it set for us!
//do we need to inform it of the activation function? I think so?
node = win.createWINNode(new PropertyObject() { { WINNode.SNodeString, NeuronType.Hidden.ToString()}});
NeuronGene newNeuronGene = new NeuronGene(node.UniqueID, NeuronType.Hidden, inputFunction);
neuronGeneList.Add(newNeuronGene);
long sourceId = potentialInputs[Utilities.Next(potentialInputs.Count)].InnovationId;
long targetId = newNeuronGene.InnovationId;
inputDummies.Add(targetId);
//aha! we must call the innovationID again, we check against win
//we don't send in any uniqueIDs so they are generated for us, and we update our idGen object
connection = win.createWINConnection(
WINConnection.ConnectionWithProperties(sourceId, targetId), idGen);
// Create a new connection with a new ID and add it to the Genome.
ConnectionGene newConnectionGene = new ConnectionGene(connection.UniqueID, connection.SourceID, connection.TargetID,
(Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange / 2.0
);
// Register the new connection with NewConnectionGeneTable.
ConnectionEndpointsStruct connectionKey = new ConnectionEndpointsStruct(sourceId, targetId);
NewConnectionGeneTable.Add(connectionKey, newConnectionGene);
// Add the new gene to this genome. We have a new ID so we can safely append the gene to the end
// of the list without risk of breaking the innovation ID order.
connectionGeneList.Add(newConnectionGene);
}
// Choose outputs uniformly at random, with replacement.
// Create dummy neurons to represent the module's outputs.
// Create connections between the output nodes and the dummy neurons.
IActivationFunction outputFunction = ActivationFunctionFactory.GetActivationFunction("ModuleOutputNeuron");
List<long> outputDummies = new List<long>(func.OutputCount);
for (int i = 0; i < func.OutputCount; i++) {
node = win.createWINNode(new PropertyObject() { { WINNode.SNodeString, NeuronType.Hidden.ToString() } });
NeuronGene newNeuronGene = new NeuronGene(node.UniqueID, NeuronType.Hidden, outputFunction);
neuronGeneList.Add(newNeuronGene);
long sourceId = newNeuronGene.InnovationId;
long targetId = potentialOutputs[Utilities.Next(potentialOutputs.Count)].InnovationId;
outputDummies.Add(sourceId);
connection = win.createWINConnection(
WINConnection.ConnectionWithProperties(sourceId, targetId), idGen);
// Create a new connection with a new ID and add it to the Genome.
ConnectionGene newConnectionGene = new ConnectionGene(connection.UniqueID, connection.SourceID, connection.TargetID,
(Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange / 2.0
);
//new ConnectionGene(idGen.NextInnovationId, sourceId, targetId,
//(Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange / 2.0);
// Register the new connection with NewConnectionGeneTable.
ConnectionEndpointsStruct connectionKey = new ConnectionEndpointsStruct(sourceId, targetId);
NewConnectionGeneTable.Add(connectionKey, newConnectionGene);
// Add the new gene to this genome. We have a new ID so we can safely append the gene to the end
// of the list without risk of breaking the innovation ID order.
connectionGeneList.Add(newConnectionGene);
}
// Pick a new ID for the new module and create it.
// Modules do not participate in history comparisons, so we will always create a new innovation ID.
// We can change this here if it becomes a problem.
//TODO: Paul check win conditions here
//this is confusing from a WIN perspective, I don't know if I'm going to support modules
//I can create a generic NextInnovationID object, but don't know if it's worth it
ModuleGene newModule = new ModuleGene(idGen.NextInnovationId, func, inputDummies, outputDummies);
moduleGeneList.Add(newModule);
}
private void Mutate_AddConnection(NeatParameters neatParameters, IdGenerator idGen, Hashtable NewConnectionGeneTable)
{
// We are always guaranteed to have enough neurons to form connections - because the input/output neurons are
// fixed. Any domain that doesn't require input/outputs is a bit nonsensical!
// Make a fixed number of attempts at finding a suitable connection to add.
if(neuronGeneList.Count>1)
{ // At least 2 neurons, so we have a chance at creating a connection.
WINManager win = WINManager.SharedWIN;
WINConnection connection;
for(int attempts=0; attempts<5; attempts++)
{
// Select candidate source and target neurons. Any neuron can be used as the source. Input neurons
// should not be used as a target
int srcNeuronIdx;
int tgtNeuronIdx;
/* Here's some code for adding connections that attempts to avoid any recursive conenctions
* within a network by only linking to neurons with innovation id's greater than the source neuron.
* Unfortunately this doesn't work because new neurons with large innovations ID's are inserted
* randomly through a network's topology! Hence this code remains here in readyness to be resurrected
* as part of some future work to support feedforward nets.
// if(ea.NeatParameters.feedForwardOnly)
// {
// /* We can ensure that all networks are feedforward only by only adding feedforward connections here.
// * Feed forward connections fall into one of the following categories. All references to indexes
// * are indexes within this genome's neuronGeneList:
// * 1) Source neuron is an input or hidden node, target is an output node.
// * 2) Source is an input or hidden node, target is a hidden node with an index greater than the source node's index.
// * 3) Source is an output node, target is an output node with an index greater than the source node's index.
// *
// * These rules are easier to understand if you understand how the different types if neuron are arranged within
// * the neuronGeneList array. Neurons are arranged in the following order:
// *
// * 1) A single bias neuron is always first.
// * 2) Experiment specific input neurons.
// * 3) Output neurons.
// * 4) Hidden neurons.
// *
// * The quantity and innovationID of all neurons within the first 3 categories remains fixed throughout the life
// * of an experiment, hence we always know where to find the bias, input and output nodes. The number of hidden nodes
// * can vary as ne nodes are created, pruned away or perhaps dropped during crossover, however they are always arranged
// * newest to oldest, or in other words sorted by innovation idea, lowest ID first.
// *
// * If output neurons were at the end of the list with hidden nodes in the middle then generating feedforward
// * connections would be as easy as selecting a target neuron with a higher index than the source neuron. However, that
// * type of arrangement is not conducive to the operation of other routines, hence this routine is a little bit more
// * complicated as a result.
// */
//
// // Ok, for a source neuron we can pick any neuron except the last output neuron.
// int neuronIdxCount = neuronGeneList.Count;
// int neuronIdxBound = neuronIdxCount-1;
//
// // Generate count-1 possibilities and avoid the last output neuron's idx.
// srcNeuronIdx = (int)Math.Floor(Utilities.NextDouble() * neuronIdxBound);
// if(srcNeuronIdx>inputBiasOutputNeuronCountMinus2) srcNeuronIdx++;
//
//
// // Now generate a target idx depending on what type of neuron srcNeuronIdx is pointing to.
// if(srcNeuronIdx<inputAndBiasNeuronCount)
// { // Source is a bias or input neuron. Target can be any output or hidden neuron.
// tgtNeuronIdx = inputAndBiasNeuronCount + (int)Math.Floor(Utilities.NextDouble() * (neuronIdxCount-inputAndBiasNeuronCount));
// }
// else if(srcNeuronIdx<inputBiasOutputNeuronCount)
// { // Source is an output neuron, but not the last output neuron. Target can be any output neuron with an index
// // greater than srcNeuronIdx.
// tgtNeuronIdx = (inputAndBiasNeuronCount+1) + (int)Math.Floor(Utilities.NextDouble() * ((inputBiasOutputNeuronCount-1)-srcNeuronIdx));
// }
// else
// { // Source is a hidden neuron. Target can be any hidden neuron after srcNeuronIdx or any output neuron.
// tgtNeuronIdx = (int)Math.Floor(Utilities.NextDouble() * ((neuronIdxBound-srcNeuronIdx)+outputNeuronCount));
//
// if(tgtNeuronIdx<outputNeuronCount)
// { // Map to an output neuron idx.
// tgtNeuronIdx += inputAndBiasNeuronCount;
// }
// else
// {
// // Map to one of the hidden neurons after srcNeuronIdx.
// tgtNeuronIdx = (tgtNeuronIdx-outputNeuronCount)+srcNeuronIdx+1;
// }
// }
// }
// // Source neuron can by any neuron. Target neuron is any neuron except input neurons.
// srcNeuronIdx = (int)Math.Floor(Utilities.NextDouble() * neuronGeneList.Count);
// tgtNeuronIdx = inputAndBiasNeuronCount + (int)Math.Floor(Utilities.NextDouble() * (neuronGeneList.Count-inputAndBiasNeuronCount));
//
// NeuronGene sourceNeuron = neuronGeneList[srcNeuronIdx];
// NeuronGene targetNeuron = neuronGeneList[tgtNeuronIdx];
// Find all potential inputs, or quit if there are not enough.
// Neurons cannot be inputs if they are dummy input nodes of a module.
NeuronGeneList potentialInputs = new NeuronGeneList();
foreach (NeuronGene n in neuronGeneList) {
if (!(n.ActivationFunction is ModuleInputNeuron)) {
potentialInputs.Add(n);
}
}
if (potentialInputs.Count < 1)
return;
// Find all potential outputs, or quit if there are not enough.
// Neurons cannot be outputs if they are dummy input or output nodes of a module, or network input or bias nodes.
NeuronGeneList potentialOutputs = new NeuronGeneList();
foreach (NeuronGene n in neuronGeneList) {
if (n.NeuronType != NeuronType.Bias && n.NeuronType != NeuronType.Input
&& !(n.ActivationFunction is ModuleInputNeuron)
&& !(n.ActivationFunction is ModuleOutputNeuron)) {
potentialOutputs.Add(n);
}
}
if (potentialOutputs.Count < 1)
return;
NeuronGene sourceNeuron = potentialInputs[Utilities.Next(potentialInputs.Count)];
NeuronGene targetNeuron = potentialOutputs[Utilities.Next(potentialOutputs.Count)];
// Check if a connection already exists between these two neurons.
long sourceId = sourceNeuron.InnovationId;
long targetId = targetNeuron.InnovationId;
if(!TestForExistingConnection(sourceId, targetId))
{
// Check if a matching mutation has already occured on another genome.
// If so then re-use the connection ID.
ConnectionEndpointsStruct connectionKey = new ConnectionEndpointsStruct(sourceId, targetId);
ConnectionGene existingConnection = (ConnectionGene)NewConnectionGeneTable[connectionKey];
ConnectionGene newConnectionGene;
if(existingConnection==null)
{
//WIN HAS ARRIVED, BITCH
//create our newest conncetion, noting the source,target and weight
connection = win.createWINConnection(
WINConnection.ConnectionWithProperties(sourceId, targetId), idGen);
// Create a new connection with a new ID and add it to the Genome.
newConnectionGene = new ConnectionGene(connection.UniqueID, connection.SourceID, connection.TargetID,
(Utilities.NextDouble() * neatParameters.connectionWeightRange / 4.0) - neatParameters.connectionWeightRange / 8.0);
//newConnectionGene =
//new ConnectionGene(idGen.NextInnovationId, sourceId, targetId,
//(Utilities.NextDouble() * neatParameters.connectionWeightRange/4.0) - neatParameters.connectionWeightRange/8.0);
// Register the new connection with NewConnectionGeneTable.
NewConnectionGeneTable.Add(connectionKey, newConnectionGene);
// Add the new gene to this genome. We have a new ID so we can safely append the gene to the end
// of the list without risk of breaking the innovation ID order.
connectionGeneList.Add(newConnectionGene);
}
else
{
//TODO: WIN should note the mutation in weight from previous connection
//WIN AIN'T HERE YET, DAWG. Nothing new being created, just adjusted weights -- which we'll need to note, but not yet
// Create a new connection, re-using the ID from existingConnection, and add it to the Genome.
newConnectionGene = new ConnectionGene(existingConnection.InnovationId, sourceId, targetId,
(Utilities.NextDouble() * neatParameters.connectionWeightRange/4.0) - neatParameters.connectionWeightRange/8.0);
// Add the new gene to this genome. We are re-using an ID so we must ensure the connection gene is
// inserted into the correct position (sorted by innovation ID).
connectionGeneList.InsertIntoPosition(newConnectionGene);
}
return;
}
}
}
// We couldn't find a valid connection to create. Instead of doing nothing lets perform connection
// weight mutation.
Mutate_ConnectionWeights(neatParameters);
}
void buildBodyExamples()
{
//we need to create random genomes, then save their generated bodies!
NeatParameters np = new NeatParameters();
IdGenerator idGen = new IdGenerator();
idGen.ResetNextInnovationNumber();
Random r = new Random();
JObject root = new JObject();
JObject meta = new JObject();
JArray genomeArray = new JArray();
//how many random input tests?
int genomeCount = 20;
meta.Add("genomeCount", genomeCount);
meta.Add("weightRange", HyperNEATParameters.weightRange);
NeatGenome seed = EvolutionManager.SharedEvolutionManager.getSeed();
int tEmpty = 0;
int emptyCount = genomeCount/4;
for (int n = genomeArray.Count; n < genomeCount; n = genomeArray.Count)
{
//create our genome
var inputCount = r.Next(4) + 3;
var outputCount = r.Next(3) + 1;
//radnom inputs 3-6, random outputs 1-3
var genome = GenomeFactory.CreateGenomePreserveID(seed, idGen);//np, idGen, inputCount, outputCount, 1);
Hashtable nodeHT = new Hashtable();
Hashtable connHT = new Hashtable();
//mutate our genome
for (int m = 0; m < 20; m++)
{
((NeatGenome)genome).Mutate(np, idGen, nodeHT, connHT);
}
//now turn genome into a network
var network = genome.Decode(null);
//turn network into JSON, and save as the network object
//genomeJSON.Add("network", JObject.FromObject(network));
//now we need a body
bool isEmptyBody;
//convert to body object
var bodyObject = simpleCom.simpleExperiment.genomeIntoBodyObject(genome, out isEmptyBody);
if ((isEmptyBody && tEmpty++ < emptyCount) || (!isEmptyBody))
{
//create object and add body info to it, then save it in our array
JObject genomeJSON = new JObject();
genomeJSON.Add("genome", JObject.FromObject(genome, new JsonSerializer() { ReferenceLoopHandling = ReferenceLoopHandling.Ignore }));
genomeJSON.Add("network", JObject.FromObject(network, new JsonSerializer() { ReferenceLoopHandling = ReferenceLoopHandling.Ignore }));
//save our body object from test
genomeJSON.Add("body", JObject.FromObject(bodyObject));
genomeJSON.Add("isEmpty", isEmptyBody.ToString());
//finally, we add our network json to the body array
genomeArray.Add(genomeJSON);
}
}
//add our networks, and add our meta information
root.Add("genomeCount", genomeArray.Count);
root.Add("genomes", genomeArray);
root.Add("meta", meta);
//and away we go! Let's save to file!
using (System.IO.StreamWriter file = new System.IO.StreamWriter("testgenomebodies.json"))
{
file.WriteLine(root.ToString());
}
}
void generateSampleCPPNs()
{
NeatParameters np = new NeatParameters();
IdGenerator idGen = new IdGenerator();
idGen.ResetNextInnovationNumber();
Random r = new Random();
JObject root = new JObject();
JObject meta = new JObject();
JArray networkArray = new JArray();
//how many random input tests?
int testCount = 100;
int networkCount = 20;
meta.Add("networkCount", networkCount);
meta.Add("sampleCount", testCount);
Console.WriteLine("All Networks start will run:" + networkCount * testCount);
for (int n = 0; n < networkCount; n++)
{
Console.WriteLine("Network start:" + n);
JObject networkJSON = new JObject();
//create our genome
var inputCount = r.Next(4) + 3;
var outputCount = r.Next(3) + 1;
//radnom inputs 3-6, random outputs 1-3
var genome = GenomeFactory.CreateGenome(np, idGen, inputCount, outputCount, 1);
Console.WriteLine("Genoem created:" + n);
Hashtable nodeHT = new Hashtable();
Hashtable connHT = new Hashtable();
//mutate our genome
for (int m = 0; m < 20; m++)
{
((NeatGenome)genome).Mutate(np, idGen, nodeHT, connHT);
Console.WriteLine("Mutation done: " + m);
}
Console.WriteLine("Mutations done:" + n);
//now turn genome into a network
var network = genome.Decode(null);
Console.WriteLine("genome decoded:" + n);
//turn network into JSON, and save as the network object
networkJSON.Add("network", JObject.FromObject(network));
JArray inputsAndOutputs = new JArray();
Console.WriteLine("starting tests:" + n);
for (var t = 0; t < testCount; t++)
{
Console.WriteLine("Test " + t + " :" + "for" + n);
JArray inputSamples = new JArray();
JArray outputSamples = new JArray();
network.ClearSignals();
Console.WriteLine("Testclear " + t + " :" + "for" + n);
//var saveInputs = new float[inputCount];
for (int ins = 0; ins < inputCount; ins++)
{
//inputs from -1,1
var inF = (float)(2 * r.NextDouble() - 1);
//saveInputs[ins] = inF;
network.SetInputSignal(ins, inF);
//add our random input
inputSamples.Add(JToken.FromObject(inF));
}
Console.WriteLine("Testrecursive next" + t + " :" + "for" + n);
//run our network, and save the response
((ModularNetwork)network).RecursiveActivation();
//network.MultipleSteps(30);
Console.WriteLine("recursive done " + t + " :" + "for" + n);
//var saveOuts = new float[outputCount];
for (var outs = 0; outs < outputCount; outs++)
{
//saveOuts[outs] = network.GetOutputSignal(outs);
//keep our outputs in an output array
outputSamples.Add(JToken.FromObject(network.GetOutputSignal(outs)));
}
//network.ClearSignals();
//network.SetInputSignals(saveInputs);
//network.MultipleSteps(30);
////((ModularNetwork)network).RecursiveActivation();
//for (var outs = 0; outs < outputCount; outs++)
//{
// Console.WriteLine("Difference in activation: " + Math.Abs(network.GetOutputSignal(outs) - saveOuts[outs]));
//}
Console.WriteLine("test reached past outputs " + t + " :" + "for" + n);
JObject test = new JObject();
test.Add("inputs", inputSamples);
test.Add("outputs", outputSamples);
inputsAndOutputs.Add(test);
Console.WriteLine("Ins/outs done " + t + " :" + "for" + n);
}
Console.WriteLine("tests ended:" + n);
//we add our inputs/outs for this json network
networkJSON.Add("tests", inputsAndOutputs);
//finally, we add our network json to the network array
networkArray.Add(networkJSON);
Console.WriteLine("Network finished:" + n);
}
Console.WriteLine("All newtorks finished, cleaning up");
//add our networks, and add our meta information
root.Add("networks", networkArray);
root.Add("meta", meta);
//and away we go! Let's save to file!
using (System.IO.StreamWriter file = new System.IO.StreamWriter("testgenomes.json"))
{
file.WriteLine(root.ToString());
}
}
/// <summary>
/// Construct a GenomeList. This can be used to construct a new Population object.
/// </summary>
/// <param name="evolutionAlgorithm"></param>
/// <param name="inputNeuronCount"></param>
/// <param name="outputNeuronCount"></param>
/// <param name="length"></param>
/// <returns></returns>
public static GenomeList CreateGenomeList(NeatParameters neatParameters, IdGenerator idGenerator, int inputNeuronCount, int outputNeuronCount, float connectionProportion, int length, bool neatBrain=false)
{
GenomeList genomeList = new GenomeList();
for(int i=0; i<length; i++)
{
idGenerator.ResetNextInnovationNumber();
genomeList.Add(CreateGenome(neatParameters, idGenerator, inputNeuronCount, outputNeuronCount, connectionProportion, neatBrain));
}
return genomeList;
}
public static IGenome CreateGenomePreserveID(IGenome seedGenome, IdGenerator idGenerator)
{
NeatGenome newGenome = new NeatGenome((NeatGenome)seedGenome, idGenerator.NextGenomeId);
// Reset the connection weights
//in this particular instance, we would take a snapshot of the genome AFTER mutation for WIN purposes. But we don't track genomes yet
foreach (ConnectionGene connectionGene in newGenome.ConnectionGeneList)
connectionGene.Weight += (0.1 - Utilities.NextDouble() * 0.2);
return newGenome;
}
public static IGenome CreateGenomePreserveID(NeatParameters neatParameters, IdGenerator idGenerator, int inputNeuronCount, int outputNeuronCount, float connectionProportion)
{
IActivationFunction actFunct;
NeuronGene neuronGene; // temp variable.
NeuronGeneList inputNeuronGeneList = new NeuronGeneList(); // includes bias neuron.
NeuronGeneList outputNeuronGeneList = new NeuronGeneList();
NeuronGeneList neuronGeneList = new NeuronGeneList();
ConnectionGeneList connectionGeneList = new ConnectionGeneList();
int nodeCount = 0;
WINManager win = WINManager.SharedWIN;
// IMPORTANT NOTE: The neurons must all be created prior to any connections. That way all of the genomes
// will obtain the same innovation ID's for the bias,input and output nodes in the initial population.
// Create a single bias neuron.
//TODO: DAVID proper activation function change to NULL?
actFunct = ActivationFunctionFactory.GetActivationFunction("NullFn");
//neuronGene = new NeuronGene(idGenerator.NextInnovationId, NeuronType.Bias, actFunct);
WINNode neuronNode = win.findOrInsertNodeWithProperties(idGenerator,
WINNode.NodeWithProperties(nodeCount++, NeuronType.Bias)
);
neuronGene = new NeuronGene(null, neuronNode.UniqueID, NeuronGene.INPUT_LAYER, NeuronType.Bias, actFunct);
inputNeuronGeneList.Add(neuronGene);
neuronGeneList.Add(neuronGene);
// Create input neuron genes.
actFunct = ActivationFunctionFactory.GetActivationFunction("NullFn");
for (int i = 0; i < inputNeuronCount; i++)
{
//TODO: DAVID proper activation function change to NULL?
//neuronGene = new NeuronGene(idGenerator.NextInnovationId, NeuronType.Input, actFunct);
neuronNode = win.findOrInsertNodeWithProperties(idGenerator, WINNode.NodeWithProperties(nodeCount++, NeuronType.Input));
neuronGene = new NeuronGene(null, neuronNode.UniqueID, NeuronGene.INPUT_LAYER, NeuronType.Input, actFunct);
inputNeuronGeneList.Add(neuronGene);
neuronGeneList.Add(neuronGene);
}
// Create output neuron genes.
//actFunct = ActivationFunctionFactory.GetActivationFunction("NullFn");
for (int i = 0; i < outputNeuronCount; i++)
{
actFunct = ActivationFunctionFactory.GetActivationFunction("BipolarSigmoid");
//actFunct = ActivationFunctionFactory.GetRandomActivationFunction(neatParameters);
//TODO: DAVID proper activation function
//neuronGene = new NeuronGene(idGenerator.NextInnovationId, NeuronType.Output, actFunct);
neuronNode = win.findOrInsertNodeWithProperties(idGenerator, WINNode.NodeWithProperties(nodeCount++, NeuronType.Output));
neuronGene = new NeuronGene(null, neuronNode.UniqueID, NeuronGene.OUTPUT_LAYER, NeuronType.Output, actFunct);
outputNeuronGeneList.Add(neuronGene);
neuronGeneList.Add(neuronGene);
}
int currentConnCount = 0;
WINConnection winConn;
// Loop over all possible connections from input to output nodes and create a number of connections based upon
// connectionProportion.
foreach (NeuronGene targetNeuronGene in outputNeuronGeneList)
{
foreach (NeuronGene sourceNeuronGene in inputNeuronGeneList)
{
// Always generate an ID even if we aren't going to use it. This is necessary to ensure connections
// between the same neurons always have the same ID throughout the generated population.
//PAUL NOTE:
//instead of generating and not using and id, we use the target and connection properties to uniquely identify a connection in WIN
//uint connectionInnovationId = idGenerator.NextInnovationId;
if (Utilities.NextDouble() < connectionProportion)
{
// Ok lets create a connection.
//first we search or create the winconnection object
winConn = win.findOrInsertConnectionWithProperties(idGenerator,
WINConnection.ConnectionWithProperties(currentConnCount, sourceNeuronGene.InnovationId, targetNeuronGene.InnovationId));
//our winconn will have our innovationID, and our weight like normal
//this will also respect the idgenerator, since it gets sent in as well, for legacy purposes
connectionGeneList.Add(new ConnectionGene(winConn.UniqueID,
sourceNeuronGene.InnovationId,
targetNeuronGene.InnovationId,
(Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange / 2.0)
);
//(Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange / 2.0)); // Weight 0 +-5
}
currentConnCount++;
}
}
//WIN will eventually be in control of all the genomes that are created as well, but not quite yet!
//TODO: WIN should be generating genomeIDs explicitly
// Don't create any hidden nodes at this point. Fundamental to the NEAT way is to start minimally!
return new NeatGenome(idGenerator.NextGenomeId, neuronGeneList, connectionGeneList, inputNeuronCount, outputNeuronCount);
}
/// <summary>
/// We define a simple neuron structure as a neuron that has a single outgoing or single incoming connection.
/// With such a structure we can easily eliminate the neuron and shift it's connections to an adjacent neuron.
/// If the neuron's non-linearity was not being used then such a mutation is a simplification of the network
/// structure that shouldn't adversly affect its functionality.
/// </summary>
private void Mutate_DeleteSimpleNeuronStructure(NeatParameters neatParameters, IdGenerator idGen, Hashtable NewConnectionGeneTable)
{
//TODO: WIN acknowledge deletion of neurongene
// We will use the NeuronConnectionLookupTable to find the simple structures.
EnsureNeuronConnectionLookupTable();
// Build a list of candidate simple neurons to choose from.
ArrayList simpleNeuronIdList = new ArrayList();
foreach(NeuronConnectionLookup lookup in neuronConnectionLookupTable.Values)
{
// If we test the connection count with <=1 then we also pick up neurons that are in dead-end circuits,
// RemoveSimpleNeuron is then able to delete these neurons from the network structure along with any
// associated connections.
// All neurons that are part of a module would appear to be dead-ended, but skip removing them anyway.
if (lookup.neuronGene.NeuronType == NeuronType.Hidden
&& !(lookup.neuronGene.ActivationFunction is ModuleInputNeuron)
&& !(lookup.neuronGene.ActivationFunction is ModuleOutputNeuron) ) {
if((lookup.incomingList.Count<=1) || (lookup.outgoingList.Count<=1))
simpleNeuronIdList.Add(lookup.neuronGene.InnovationId);
}
}
// Are there any candiate simple neurons?
if(simpleNeuronIdList.Count==0)
{ // No candidate neurons. As a fallback lets delete a connection.
Mutate_DeleteConnection();
return;
}
// Pick a simple neuron at random.
int idx = (int)Math.Floor(Utilities.NextDouble() * simpleNeuronIdList.Count);
long neuronId = (long)simpleNeuronIdList[idx];
RemoveSimpleNeuron(neuronId, neatParameters, idGen, NewConnectionGeneTable);
}
/// <summary>
/// Create a default minimal genome that describes a NN with the given number of inputs and outputs.
/// </summary>
/// <returns></returns>
public static IGenome CreateGenome(NeatParameters neatParameters, IdGenerator idGenerator, int inputNeuronCount, int outputNeuronCount, int outputsPerPolicy, float connectionProportion)
{
IActivationFunction actFunct;
NeuronGene neuronGene; // temp variable.
NeuronGeneList inputNeuronGeneList = new NeuronGeneList(); // includes bias neuron.
NeuronGeneList outputNeuronGeneList = new NeuronGeneList();
NeuronGeneList neuronGeneList = new NeuronGeneList();
ConnectionGeneList connectionGeneList = new ConnectionGeneList();
// IMPORTANT NOTE: The neurons must all be created prior to any connections. That way all of the genomes
// will obtain the same innovation ID's for the bias,input and output nodes in the initial population.
// Create a single bias neuron.
//TODO: DAVID proper activation function change to NULL?
actFunct = ActivationFunctionFactory.GetActivationFunction("NullFn");
//neuronGene = new NeuronGene(idGenerator.NextInnovationId, NeuronType.Bias, actFunct);
neuronGene = new NeuronGene(null, idGenerator.NextInnovationId, NeuronGene.INPUT_LAYER, NeuronType.Bias, actFunct);
inputNeuronGeneList.Add(neuronGene);
neuronGeneList.Add(neuronGene);
// Create input neuron genes.
actFunct = ActivationFunctionFactory.GetActivationFunction("NullFn");
for(int i=0; i<inputNeuronCount; i++)
{
//TODO: DAVID proper activation function change to NULL?
//neuronGene = new NeuronGene(idGenerator.NextInnovationId, NeuronType.Input, actFunct);
neuronGene = new NeuronGene(null, idGenerator.NextInnovationId, NeuronGene.INPUT_LAYER, NeuronType.Input, actFunct);
inputNeuronGeneList.Add(neuronGene);
neuronGeneList.Add(neuronGene);
}
// Create output neuron genes.
//actFunct = ActivationFunctionFactory.GetActivationFunction("NullFn");
for(int i=0; i<outputNeuronCount; i++)
{
actFunct = ActivationFunctionFactory.GetActivationFunction("BipolarSigmoid");
//actFunct = ActivationFunctionFactory.GetRandomActivationFunction(neatParameters);
//TODO: DAVID proper activation function
//neuronGene = new NeuronGene(idGenerator.NextInnovationId, NeuronType.Output, actFunct);
neuronGene = new NeuronGene(null, idGenerator.NextInnovationId, NeuronGene.OUTPUT_LAYER, NeuronType.Output, actFunct);
outputNeuronGeneList.Add(neuronGene);
neuronGeneList.Add(neuronGene);
}
// Loop over all possible connections from input to output nodes and create a number of connections based upon
// connectionProportion.
foreach(NeuronGene targetNeuronGene in outputNeuronGeneList)
{
foreach(NeuronGene sourceNeuronGene in inputNeuronGeneList)
{
// Always generate an ID even if we aren't going to use it. This is necessary to ensure connections
// between the same neurons always have the same ID throughout the generated population.
uint connectionInnovationId = idGenerator.NextInnovationId;
if(Utilities.NextDouble() < connectionProportion)
{ // Ok lets create a connection.
connectionGeneList.Add( new ConnectionGene(connectionInnovationId,
sourceNeuronGene.InnovationId,
targetNeuronGene.InnovationId,
(Utilities.NextDouble() * neatParameters.connectionWeightRange ) - neatParameters.connectionWeightRange/2.0)); // Weight 0 +-5
}
}
}
// Don't create any hidden nodes at this point. Fundamental to the NEAT way is to start minimally!
// Schrum: Added outputsPerPolicy: If outputsPerPolicy == outputNeuronCount, then behaves like default NEAT
return new NeatGenome(idGenerator.NextGenomeId, neuronGeneList, connectionGeneList, inputNeuronCount, outputNeuronCount, outputsPerPolicy);
}
private void RemoveSimpleNeuron(long neuronId, NeatParameters neatParameters, IdGenerator idGen, Hashtable NewConnectionGeneTable)
{
WINManager win = WINManager.SharedWIN;
//WINNode node;
WINConnection connection;
// Create new connections that connect all of the incoming and outgoing neurons
// that currently exist for the simple neuron.
NeuronConnectionLookup lookup = (NeuronConnectionLookup)neuronConnectionLookupTable[neuronId];
foreach(ConnectionGene incomingConnection in lookup.incomingList)
{
foreach(ConnectionGene outgoingConnection in lookup.outgoingList)
{
if(TestForExistingConnection(incomingConnection.SourceNeuronId, outgoingConnection.TargetNeuronId))
{ // Connection already exists.
continue;
}
// Test for matching connection within NewConnectionGeneTable.
ConnectionEndpointsStruct connectionKey = new ConnectionEndpointsStruct(incomingConnection.SourceNeuronId,
outgoingConnection.TargetNeuronId);
ConnectionGene existingConnection = (ConnectionGene)NewConnectionGeneTable[connectionKey];
ConnectionGene newConnectionGene;
if(existingConnection==null)
{
// No matching connection found. Create a connection with a new ID.
//create our newest conncetion, noting the source,target and weight
connection = win.createWINConnection(
WINConnection.ConnectionWithProperties(incomingConnection.SourceNeuronId, outgoingConnection.TargetNeuronId), idGen);
// Create a new connection with a new ID and add it to the Genome.
newConnectionGene = new ConnectionGene(connection.UniqueID, connection.SourceID, connection.TargetID,
(Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange / 2.0
);
//newConnectionGene = new ConnectionGene(idGen.NextInnovationId,
// incomingConnection.SourceNeuronId,
// outgoingConnection.TargetNeuronId,
// (Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange/2.0);
// Register the new ID with NewConnectionGeneTable.
NewConnectionGeneTable.Add(connectionKey, newConnectionGene);
// Add the new gene to the genome.
connectionGeneList.Add(newConnectionGene);
}
else
{
//WIN should acknowledge change in individual here
// Matching connection found. Re-use its ID.
newConnectionGene = new ConnectionGene(existingConnection.InnovationId,
incomingConnection.SourceNeuronId,
outgoingConnection.TargetNeuronId,
(Utilities.NextDouble() * neatParameters.connectionWeightRange) - neatParameters.connectionWeightRange/2.0);
// Add the new gene to the genome. Use InsertIntoPosition() to ensure we don't break the sort
// order of the connection genes.
connectionGeneList.InsertIntoPosition(newConnectionGene);
}
}
}
// Delete the old connections.
foreach(ConnectionGene incomingConnection in lookup.incomingList)
connectionGeneList.Remove(incomingConnection);
foreach(ConnectionGene outgoingConnection in lookup.outgoingList)
{
// Filter out recurrent connections - they will have already been
// deleted in the loop through 'lookup.incomingList'.
if(outgoingConnection.TargetNeuronId != neuronId)
connectionGeneList.Remove(outgoingConnection);
}
// Delete the simple neuron - it no longer has any connections to or from it.
neuronGeneList.Remove(neuronId);
}
/// <summary>
/// Construct a GenomeList. This can be used to construct a new Population object.
/// </summary>
/// <param name="evolutionAlgorithm"></param>
/// <param name="inputNeuronCount"></param>
/// <param name="outputNeuronCount"></param>
/// <param name="length"></param>
/// <returns></returns>
// Schrum: Added outputsPerPolicy
public static GenomeList CreateGenomeList(NeatParameters neatParameters, IdGenerator idGenerator, int inputNeuronCount, int outputNeuronCount, int outputsPerPolicy, float connectionProportion, int length)
{
GenomeList genomeList = new GenomeList();
for(int i=0; i<length; i++)
{
idGenerator.ResetNextInnovationNumber();
// Schrum: Added outputsPerPolicy
genomeList.Add(CreateGenome(neatParameters, idGenerator, inputNeuronCount, outputNeuronCount, outputsPerPolicy, connectionProportion));
}
return genomeList;
}
public IGenome CreateOffspring_Asexual(NeatParameters neatParameters, IdGenerator idGen, Hashtable newNeuronTable, Hashtable newConnectionTable)
{
// Make an exact copy this Genome.
NeatGenome offspring = new NeatGenome(this, idGen.NextGenomeId);
// Mutate the new genome.
//WIN acknowledges any connection or node mutations, but doesn't save any other mutations
offspring.Mutate(neatParameters, idGen, newNeuronTable, newConnectionTable);
return offspring;
}
static void Main(string[] args)
{
string folder = "";
NeatGenome seedGenome = null;
string filename = null;
string shape = "triangle";
bool isMulti = false;
for (int j = 0; j < args.Length; j++)
{
if(j <= args.Length - 2)
switch (args[j])
{
case "-seed": filename = args[++j];
Console.WriteLine("Attempting to use seed from file " + filename);
break;
case "-folder": folder = args[++j];
Console.WriteLine("Attempting to output to folder " + folder);
break;
case "-shape": shape = args[++j];
Console.WriteLine("Attempting to do experiment with shape " + shape);
break;
case "-multi": isMulti = Boolean.Parse(args[++j]);
Console.WriteLine("Experiment is heterogeneous? " + isMulti);
break;
}
}
if(filename!=null)
{
try
{
XmlDocument document = new XmlDocument();
document.Load(filename);
seedGenome = XmlNeatGenomeReaderStatic.Read(document);
}
catch (Exception e)
{
System.Console.WriteLine("Problem loading genome. \n" + e.Message);
}
}
double maxFitness = 0;
int maxGenerations = 1000;
int populationSize = 150;
int inputs = 4;
IExperiment exp = new SkirmishExperiment(inputs, 1, isMulti, shape);
StreamWriter SW;
SW = File.CreateText(folder + "logfile.txt");
XmlDocument doc;
FileInfo oFileInfo;
IdGenerator idgen;
EvolutionAlgorithm ea;
if (seedGenome == null)
{
idgen = new IdGenerator();
ea = new EvolutionAlgorithm(new Population(idgen, GenomeFactory.CreateGenomeList(exp.DefaultNeatParameters, idgen, exp.InputNeuronCount, exp.OutputNeuronCount, exp.DefaultNeatParameters.pInitialPopulationInterconnections, populationSize)), exp.PopulationEvaluator, exp.DefaultNeatParameters);
}
else
{
idgen = new IdGeneratorFactory().CreateIdGenerator(seedGenome);
ea = new EvolutionAlgorithm(new Population(idgen, GenomeFactory.CreateGenomeList(seedGenome, populationSize, exp.DefaultNeatParameters, idgen)), exp.PopulationEvaluator, exp.DefaultNeatParameters);
}
for (int j = 0; j < maxGenerations; j++)
{
DateTime dt = DateTime.Now;
ea.PerformOneGeneration();
if (ea.BestGenome.Fitness > maxFitness)
{
maxFitness = ea.BestGenome.Fitness;
doc = new XmlDocument();
XmlGenomeWriterStatic.Write(doc, (NeatGenome)ea.BestGenome);
oFileInfo = new FileInfo(folder + "bestGenome" + j.ToString() + ".xml");
doc.Save(oFileInfo.FullName);
// This will output the substrate, uncomment if you want that
/* doc = new XmlDocument();
XmlGenomeWriterStatic.Write(doc, (NeatGenome) SkirmishNetworkEvaluator.substrate.generateMultiGenomeModulus(ea.BestGenome.Decode(null),5));
oFileInfo = new FileInfo(folder + "bestNetwork" + j.ToString() + ".xml");
doc.Save(oFileInfo.FullName);
*/
}
Console.WriteLine(ea.Generation.ToString() + " " + ea.BestGenome.Fitness + " " + (DateTime.Now.Subtract(dt)));
//Do any post-hoc stuff here
SW.WriteLine(ea.Generation.ToString() + " " + (maxFitness).ToString());
}
SW.Close();
doc = new XmlDocument();
XmlGenomeWriterStatic.Write(doc, (NeatGenome)ea.BestGenome, ActivationFunctionFactory.GetActivationFunction("NullFn"));
oFileInfo = new FileInfo(folder + "bestGenome.xml");
doc.Save(oFileInfo.FullName);
}
public IGenome CreateOffspring_Sexual(NeatParameters np, IdGenerator idGen, IGenome parent)
{
NeatGenome otherParent = parent as NeatGenome;
if (otherParent == null)
return null;
// Build a list of connections in either this genome or the other parent.
CorrelationResults correlationResults = CorrelateConnectionGeneLists(connectionGeneList, otherParent.connectionGeneList);
Debug.Assert(correlationResults.PerformIntegrityCheck(), "CorrelationResults failed integrity check.");
//----- Connection Genes.
// We will temporarily store the offspring's genes in newConnectionGeneList and keeping track of which genes
// exist with newConnectionGeneTable. Here we ensure these objects are created, and if they already existed
// then ensure they are cleared. Clearing existing objects is more efficient that creating new ones because
// allocated memory can be re-used.
// Key = connection key, value = index in newConnectionGeneList.
if (newConnectionGeneTable == null)
{ // Provide a capacity figure to the new Hashtable. The offspring will be the same length (or thereabouts).
newConnectionGeneTable = new Hashtable(connectionGeneList.Count);
}
else
{
newConnectionGeneTable.Clear();
}
//TODO: No 'capacity' constructor on CollectionBase. Create modified/custom CollectionBase.
// newConnectionGeneList must be constructed on each call because it is passed to a new NeatGenome
// at construction time and a permanent reference to the list is kept.
newConnectionGeneList = new ConnectionGeneList(ConnectionGeneList.Count);
// A switch that stores which parent is fittest 1 or 2. Chooses randomly if both are equal. More efficient to calculate this just once.
byte fitSwitch;
if (Fitness > otherParent.Fitness)
fitSwitch = 1;
else if (Fitness < otherParent.Fitness)
fitSwitch = 2;
else
{ // Select one of the parents at random to be the 'master' genome during crossover.
if (Utilities.NextDouble() < 0.5)
fitSwitch = 1;
else
fitSwitch = 2;
}
bool combineDisjointExcessFlag = Utilities.NextDouble() < np.pDisjointExcessGenesRecombined;
// Loop through the correlationResults, building a table of ConnectionGenes from the parents that will make it into our
// new [single] offspring. We use a table keyed on connection end points to prevent passing connections to the offspring
// that may have the same end points but a different innovation number - effectively we filter out duplicate connections.
int idxBound = correlationResults.CorrelationItemList.Count;
for (int i = 0; i < idxBound; i++)
{
CreateOffspring_Sexual_ProcessCorrelationItem((CorrelationItem)correlationResults.CorrelationItemList[i], fitSwitch, combineDisjointExcessFlag, np);
}
//----- Neuron Genes.
// Build a neuronGeneList by analysing each connection's neuron end-point IDs.
// This strategy has the benefit of eliminating neurons that are no longer connected too.
// Remember to always keep all input, output and bias neurons though!
NeuronGeneList newNeuronGeneList = new NeuronGeneList(neuronGeneList.Count);
// Keep a table of the NeuronGene ID's keyed by ID so that we can keep track of which ones have been added.
// Key = innovation ID, value = null for some reason.
if (newNeuronGeneTable == null)
newNeuronGeneTable = new Hashtable(neuronGeneList.Count);
else
newNeuronGeneTable.Clear();
// Get the input/output neurons from this parent. All Genomes share these neurons, they do not change during a run.
idxBound = neuronGeneList.Count;
for (int i = 0; i < idxBound; i++)
{
if (neuronGeneList[i].NeuronType != NeuronType.Hidden)
{
newNeuronGeneList.Add(new NeuronGene(neuronGeneList[i]));
newNeuronGeneTable.Add(neuronGeneList[i].InnovationId, null);
}
else
{ // No more bias, input or output nodes. break the loop.
break;
}
}
// Now analyse the connections to determine which NeuronGenes are required in the offspring.
// Loop through every connection in the child, and add to the child those hidden neurons that are sources or targets of the connection.
idxBound = newConnectionGeneList.Count;
for (int i = 0; i < idxBound; i++)
{
NeuronGene neuronGene;
ConnectionGene connectionGene = newConnectionGeneList[i];
if (!newNeuronGeneTable.ContainsKey(connectionGene.SourceNeuronId))
{
//TODO: DAVID proper activation function
// We can safely assume that any missing NeuronGenes at this point are hidden heurons.
neuronGene = this.neuronGeneList.GetNeuronById(connectionGene.SourceNeuronId);
if (neuronGene != null)
newNeuronGeneList.Add(new NeuronGene(neuronGene));
else
newNeuronGeneList.Add(new NeuronGene(otherParent.NeuronGeneList.GetNeuronById(connectionGene.SourceNeuronId)));
//newNeuronGeneList.Add(new NeuronGene(connectionGene.SourceNeuronId, NeuronType.Hidden, ActivationFunctionFactory.GetActivationFunction("SteepenedSigmoid")));
newNeuronGeneTable.Add(connectionGene.SourceNeuronId, null);
}
if (!newNeuronGeneTable.ContainsKey(connectionGene.TargetNeuronId))
{
//TODO: DAVID proper activation function
// We can safely assume that any missing NeuronGenes at this point are hidden heurons.
neuronGene = this.neuronGeneList.GetNeuronById(connectionGene.TargetNeuronId);
if (neuronGene != null)
newNeuronGeneList.Add(new NeuronGene(neuronGene));
else
newNeuronGeneList.Add(new NeuronGene(otherParent.NeuronGeneList.GetNeuronById(connectionGene.TargetNeuronId)));
//newNeuronGeneList.Add(new NeuronGene(connectionGene.TargetNeuronId, NeuronType.Hidden, ActivationFunctionFactory.GetActivationFunction("SteepenedSigmoid")));
newNeuronGeneTable.Add(connectionGene.TargetNeuronId, null);
}
}
// Determine which modules to pass on to the child in the same way.
// For each module in this genome or in the other parent, if it was referenced by even one connection add it and all its dummy neurons to the child.
List<ModuleGene> newModuleGeneList = new List<ModuleGene>();
// Build a list of modules the child might have, which is a union of the parents' module lists, but they are all copies so we can't just do a union.
List<ModuleGene> unionParentModules = new List<ModuleGene>(moduleGeneList);
foreach (ModuleGene moduleGene in otherParent.moduleGeneList)
{
bool alreadySeen = false;
foreach (ModuleGene match in unionParentModules)
{
if (moduleGene.InnovationId == match.InnovationId)
{
alreadySeen = true;
break;
}
}
if (!alreadySeen)
{
unionParentModules.Add(moduleGene);
}
}
foreach (ModuleGene moduleGene in unionParentModules)
{
// Examine each neuron in the child to determine whether it is part of a module.
foreach (List<long> dummyNeuronList in new List<long>[] { moduleGene.InputIds, moduleGene.OutputIds })
{
foreach (long dummyNeuronId in dummyNeuronList)
{
if (newNeuronGeneTable.ContainsKey(dummyNeuronId))
{
goto childHasModule;
}
}
}
continue; // the child does not contain this module, so continue the loop and check for the next module.
childHasModule: // the child does contain this module, so make sure the child gets all the nodes the module requires to work.
// Make sure the child has all the neurons in the given module.
newModuleGeneList.Add(new ModuleGene(moduleGene));
foreach (List<long> dummyNeuronList in new List<long>[] { moduleGene.InputIds, moduleGene.OutputIds })
{
foreach (long dummyNeuronId in dummyNeuronList)
{
if (!newNeuronGeneTable.ContainsKey(dummyNeuronId))
{
newNeuronGeneTable.Add(dummyNeuronId, null);
NeuronGene neuronGene = this.neuronGeneList.GetNeuronById(dummyNeuronId);
if (neuronGene != null)
{
newNeuronGeneList.Add(new NeuronGene(neuronGene));
}
else
{
newNeuronGeneList.Add(new NeuronGene(otherParent.NeuronGeneList.GetNeuronById(dummyNeuronId)));
}
}
}
}
}
// TODO: Inefficient code?
newNeuronGeneList.SortByInnovationId();
//PAUL: WIN should go here some more!
//in the future, we're going to call out to WIN to create our NeatGenome for us, where it will save it
//TODO: WIN calls for sexual reproduction
// newConnectionGeneList is already sorted because it was generated by passing over the list returned by
// CorrelateConnectionGeneLists() - which is always in order.
return new NeatGenome(idGen.NextGenomeId, newNeuronGeneList, newModuleGeneList, newConnectionGeneList, inputNeuronCount, outputNeuronCount);
}
public void initializeEvolution(int populationSize)
{
logOutput = new StreamWriter(outputFolder + "logfile.txt");
IdGenerator idgen = new IdGenerator();
ea = new EvolutionAlgorithm(new Population(idgen, GenomeFactory.CreateGenomeList(experiment.DefaultNeatParameters, idgen, experiment.InputNeuronCount, experiment.OutputNeuronCount, experiment.OutputsPerPolicy, experiment.DefaultNeatParameters.pInitialPopulationInterconnections, populationSize)), experiment.PopulationEvaluator, experiment.DefaultNeatParameters);
}
/// <summary>
/// Paul: Modified the mutation function to take in the required objects, instead of Evolution Algorithm.
/// This way, mutation isn't tied to a large EA object, but can still function without issue. Useful for interactive evolution framework.
/// </summary>
/// <param name="neatParameters"></param>
/// <param name="idGen"></param>
/// <param name="genomeHashtable"></param>
/// <param name="connectionHashTable"></param>
public void Mutate(NeatParameters neatParameters, IdGenerator idGen, Hashtable genomeHashtable, Hashtable connectionHashTable)
{
// Determine the type of mutation to perform.
double[] probabilities = new double[]
{
neatParameters.pMutateAddNode,
neatParameters.pMutateAddModule,
neatParameters.pMutateAddConnection,
neatParameters.pMutateDeleteConnection,
neatParameters.pMutateDeleteSimpleNeuron,
neatParameters.pMutateConnectionWeights
};
int outcome = RouletteWheel.SingleThrow(probabilities);
switch(outcome)
{
case 0:
//basic support by WIN, but doesn't acknowledge weight changes
Mutate_AddNode(neatParameters, idGen, genomeHashtable);
break;
case 1:
//currently not totally supported by WIN
Mutate_AddModule(neatParameters, idGen, connectionHashTable);
break;
case 2:
//WIN basic support, doesn't acknowledge weight changes
Mutate_AddConnection(neatParameters, idGen, connectionHashTable);
break;
case 3:
//Doesn't acknowledge weight changes yet
Mutate_DeleteConnection();
break;
case 4:
//WIN doesn't acknowledge deletion of neurons yet
Mutate_DeleteSimpleNeuronStructure(neatParameters, idGen, connectionHashTable);
break;
case 5:
//Win doesn't yet acknowledge the weight changes
Mutate_ConnectionWeights(neatParameters);
break;
}
}
/// <summary>
/// Initializes the EA with a random intial population.
/// </summary>
public void initializeEvolution(int populationSize)
{
LogOutput = Logging ? new StreamWriter(Path.Combine(OutputFolder, "log.txt")) : null;
FinalPositionOutput = FinalPositionLogging ? new StreamWriter(Path.Combine(OutputFolder,"final-position.txt")) : null;
ArchiveModificationOutput = FinalPositionLogging ? new StreamWriter(Path.Combine(OutputFolder, "archive-mods.txt")) : null;
ComplexityOutput = new StreamWriter(Path.Combine(OutputFolder, "complexity.txt"));
ComplexityOutput.WriteLine("avg,stdev,min,max");
if (FinalPositionLogging)
{
FinalPositionOutput.WriteLine("ID,x,y");
ArchiveModificationOutput.WriteLine("ID,action,time,x,y");
}
IdGenerator idgen = new IdGenerator();
EA = new EvolutionAlgorithm(new Population(idgen, GenomeFactory.CreateGenomeList(experiment.DefaultNeatParameters, idgen, experiment.InputNeuronCount, experiment.OutputNeuronCount, experiment.DefaultNeatParameters.pInitialPopulationInterconnections, populationSize, SimExperiment.neatBrain)), experiment.PopulationEvaluator, experiment.DefaultNeatParameters);
EA.outputFolder = OutputFolder;
EA.neatBrain = NEATBrain;
}
public static GenomeList CreateGenomeListPreserveIDs(NeatParameters neatParameters, IdGenerator idGenerator,
int inputNeuronCount, int outputNeuronCount, float connectionProportion, int length, AssessGenotypeFunction assess)
{
GenomeList genomeList = new GenomeList();
int testCount = 0; int maxTests = 5;
//for (int i = 0; i < length; i++)
while(genomeList.Count < length)
{
IGenome genome = CreateGenomePreserveID(neatParameters, idGenerator, inputNeuronCount, outputNeuronCount, connectionProportion);
if (assess != null && assess(genome) && testCount++ < maxTests)
{
//after adding the genome, reset test count
genomeList.Add(genome);
testCount = 0;
}
else if (assess == null)
genomeList.Add(genome);
else if (testCount >= maxTests)
{
genomeList.Add(genome);
testCount = 0;
}
}
return genomeList;
}
