/// <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;
}
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());
}
}
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());
}
}
/// <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;
}