Esempio n. 1
0
        static void RunTrial(int offset)
        {
            RESULTS_FILE = EXPERIMENTS_DIR + RESULTS_FILE_BASE + offset + ".csv";
            _random      = new FastRandom();

            _experiment = new SocialExperiment();
            XmlDocument xmlConfig = new XmlDocument();

            xmlConfig.Load(CONFIG_FILE);
            _experiment.Initialize("SimpleEvolution", xmlConfig.DocumentElement);
            _experiment.NeatGenomeParameters.AddConnectionMutationProbability    = 0;
            _experiment.NeatGenomeParameters.AddNodeMutationProbability          = 0;
            _experiment.NeatGenomeParameters.DeleteConnectionMutationProbability = 0;

            SocialExperiment.CreateNetwork(FEED_FORWARD_NETWORK_FILE, _experiment.InputCount, _experiment.OutputCount);

            // Record the changes at each step
            _experiment.World.Stepped += new social_learning.World.StepEventHandler(World_Stepped);

            // Read in the seed genome from file. This is the prototype for our other population of networks.
            var seed = _experiment.LoadPopulation(XmlReader.Create(FEED_FORWARD_NETWORK_FILE))[0];

            // Create a genome factory with our neat genome parameters object and the appropriate number of input and output neuron genes.
            IGenomeFactory <NeatGenome> genomeFactory = _experiment.CreateGenomeFactory();

            // Create an initial population of randomly generated genomes.
            List <NeatGenome> genomeList = genomeFactory.CreateGenomeList(_experiment.DefaultPopulationSize, 0, seed);

            // Randomize the genomes
            RandomizeGenomes(genomeList);

            // Create genome decoder.
            IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = _experiment.CreateGenomeDecoder();

            // Create the evaluator that will handle the simulation
            _evaluator = new ForagingEvaluator <NeatGenome>(genomeDecoder, _experiment.World, AgentTypes.Social)
            {
                MaxTimeSteps             = 200000UL,
                BackpropEpochsPerExample = 1
            };

            using (TextWriter writer = new StreamWriter(RESULTS_FILE))
                writer.WriteLine("Step,Best,Average");

            // Start the simulation
            _evaluator.Evaluate(genomeList);
        }
Esempio n. 2
0
        static void Main(string[] args)
        {
            _random = new FastRandom();

            _experiment = new SocialExperiment();
            XmlDocument xmlConfig = new XmlDocument();

            xmlConfig.Load(CONFIG_FILE);
            _experiment.Initialize("SimpleEvolution", xmlConfig.DocumentElement);
            _experiment.NeatGenomeParameters.AddConnectionMutationProbability    = 0;
            _experiment.NeatGenomeParameters.AddNodeMutationProbability          = 0;
            _experiment.NeatGenomeParameters.DeleteConnectionMutationProbability = 0;

            SocialExperiment.CreateNetwork(FEED_FORWARD_NETWORK_FILE, _experiment.InputCount, 20, _experiment.OutputCount);

            // Record the changes at each step
            _experiment.World.Stepped += new social_learning.World.StepEventHandler(World_Stepped);

            // Read in the teacher genome from file.
            var agentGenome = _experiment.LoadPopulation(XmlReader.Create(FEED_FORWARD_NETWORK_FILE));

            // Create genome decoder.
            IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = _experiment.CreateGenomeDecoder();

            // Create the evaluator that will handle the simulation
            _evaluator = new ForagingEvaluator <NeatGenome>(genomeDecoder, _experiment.World, AgentTypes.QLearning)
            {
                MaxTimeSteps             = 50000000UL,
                BackpropEpochsPerExample = 1
            };

            using (TextWriter writer = new StreamWriter(RESULTS_FILE))
                writer.WriteLine("Step,Score");

            // Start the simulation
            _evaluator.Evaluate(agentGenome);
        }
Esempio n. 3
0
        private void startQLearning()
        {
            SocialExperiment.CreateNetwork(QLEARNING_FEED_FORWARD_NETWORK_FILE, _experiment.InputCount, 20, _experiment.OutputCount);

            // Read in the teacher genome from file.
            var agentGenome = _experiment.LoadPopulation(XmlReader.Create(QLEARNING_FEED_FORWARD_NETWORK_FILE));

            // Create genome decoder.
            IGenomeDecoder <NeatGenome, IBlackBox> genomeDecoder = _experiment.CreateGenomeDecoder();

            // Create the evaluator that will handle the simulation
            _experiment.Evaluator = new ForagingEvaluator <NeatGenome>(genomeDecoder, _experiment.World, AgentTypes.QLearning)
            {
                MaxTimeSteps             = 50000000UL,
                BackpropEpochsPerExample = 1,
                LogDiversity             = false
            };

            // Add the world reset
            _experiment.World.Stepped += new World.StepEventHandler(World_Stepped);

            // Start the simulation
            _experiment.Evaluator.Evaluate(agentGenome);
        }