/// <summary>
/// Initialize a new <see cref="LanderIndividual"/> instance with Random values.
/// </summary>
public LanderIndividual(Random random)
{
// NOTE: network topology defined here
this.neuralNet = new NeuralNetwork();
this.neuralNet.InputCount = 7;
this.neuralNet.OutputCount = 2;
this.neuralNet.AddHiddenLayer(5);
this.RandomGenerator = random;
// Initialize the weights with random values between -1.0 and 1.0
this.weights = this.neuralNet.GetAllWeights();
for (int i = 0; i < this.weights.Count; i++)
{
this.weights[i] = this.RandomGenerator.NextDouble() * (weightMax - weightMin) - (weightMax - weightMin) / 2;
}
this.neuralNet.SetAllWeights(this.weights);
}
/// <summary>
/// Run the genetic algorithm to train the neural network
/// </summary>
private void ExecuteTrainCommand()
{
this.ExecuteStopCommand();
// The background worker allows the GA to be run in a different thread
BackgroundWorker backgroundWorker = new BackgroundWorker();
// Setup of the genetic algorithm
LanderIndividualSettings landerIndividualSettings = new LanderIndividualSettings();
LanderIndividualFactory landerFactory = new LanderIndividualFactory();
GeneticAlgorithm.GeneticAlgorithm ga = new GeneticAlgorithm.GeneticAlgorithm(landerFactory);
LanderIndividual best = null;
int currentIteration = 0;
// Set up the ga
this.environment.Gravity = 2.0;
this.environment.WindSpeed = 0.1;
landerIndividualSettings.StartingFuel = 100;
landerIndividualSettings.StartingHeight = 100;
landerIndividualSettings.StartingHorizontal = 0;
landerIndividualSettings.LanderEnvironment = this.environment;
landerIndividualSettings.CrossoverAlgorithm = LanderIndividualSettings.CrossoverType.OnePoint;
ga.SelectionType = GeneticAlgorithm.GeneticAlgorithm.SelectionTypes.Tournament;
ga.TournamentSize = 4;
ga.CrossoverProbability = 0;
ga.MutationProbability = 1;
ga.CalculationLimit = 60000;
ga.ElitistCount = 4;
ga.PopulationSize = 100;
landerFactory.IndividualSettings = landerIndividualSettings;
// This lambda function handles the iteration events from the ga.
EventHandler<IterationEventArgs> handler = (sender, args) =>
{
backgroundWorker.ReportProgress(0, args);
};
// Set the work lambda function.
backgroundWorker.DoWork += (sender, e) =>
{
// Add the iteration event handler to report progress back to the main thread
ga.IterationEvent += handler;
// Run the ga
best = (LanderIndividual)ga.Run(landerIndividualSettings);
ga.IterationEvent -= handler;
};
// Update the graph to show progress
backgroundWorker.ProgressChanged += (sender, e) =>
{
this.MinFitnessValues.Add(new Tuple<int, double>(currentIteration, ((IterationEventArgs)e.UserState).MinFitness));
this.MaxFitnessValues.Add(new Tuple<int, double>(currentIteration, ((IterationEventArgs)e.UserState).MaxFitness));
this.AvgFitnessValues.Add(new Tuple<int, double>(currentIteration, ((IterationEventArgs)e.UserState).AverageFitness));
currentIteration++;
if (this.MinFitnessValues.Count > 600)
{
this.MinFitnessValues.Clear();
this.MaxFitnessValues.Clear();
this.AvgFitnessValues.Clear();
}
};
backgroundWorker.RunWorkerCompleted += (sender, e) =>
{
this.IsTraining = false;
// Save the resulting neural network
this.neuralNetwork = best.CurrentNeuralNetwork;
Debug.WriteLine(this.neuralNetwork.ToString());
};
// Clear out previous chart data and run the background worker
this.MinFitnessValues.Clear();
this.MaxFitnessValues.Clear();
this.AvgFitnessValues.Clear();
backgroundWorker.WorkerReportsProgress = true;
this.IsTraining = true;
backgroundWorker.RunWorkerAsync();
}
public void Net1()
{
NeuralNetwork net = new NeuralNetwork();
net.InputCount = 2;
net.OutputCount = 2;
}
static void Main(string[] args)
{
bool quit = false;
string input;
// NOTE: network topology defined here
neuralNetwork = new NeuralNetwork();
neuralNetwork.InputCount = 7;
neuralNetwork.OutputCount = 2;
neuralNetwork.AddHiddenLayer(5);
PrintHelp();
while (quit == false)
{
Console.Write("> ");
input = Console.ReadLine();
switch (input)
{
case "q":
case "quit":
quit = true;
break;
case "t":
case "train":
Train(true);
break;
case "tl":
case "trainlong":
TrainLong();
break;
case "r":
case "run":
RunSimulation();
break;
case "ra":
case "runall":
RunSimulationVarying(true);
break;
case "h":
case "help":
PrintHelp();
break;
case "p":
case "print":
PrintNetwork();
break;
case "rs":
case "reset":
ResetNetwork();
break;
case "rg":
case "rungeneralize":
RunSimulationGeneralize();
break;
default:
Console.WriteLine("Unrecognized command. Try 'help'");
break;
}
}
}