/// <summary>
/// 存储在内存中
/// </summary>
/// <returns></returns>
public (byte[] actorBuffer, byte[] cirticBuffer, string innerTypeName, int actionsNum, int featuresNum, int[] actionKeys) PersistencMemory()
{
//actor and critic must be the same type
string innerTypeName = _actorNet.GetType().Name;
byte[] actorBuffer = _actorNet.PersistenceMemory();
byte[] cirticBuffer = _criticNet.PersistenceMemory();
int[] actionKeys = Env.RandomSeedKeys;
return(actorBuffer, cirticBuffer, innerTypeName, _actionsNumber, _featuresNumber, actionKeys);
}
public void Accept(ISupportNet sourceNet)
{
//convert to bytes
byte[] bytes = sourceNet.PersistenceMemory();
//read model and set parameters
classifierOutput = Function.Load(bytes, device);
inputVariable = classifierOutput.Inputs.First(v => v.Name == "inputVariable");
outputVariable = Variable.InputVariable(classifierOutput.Output.Shape, DataType.Float, "labelVariable");
var trainingLoss = CNTKLib.SquaredError(classifierOutput, outputVariable);
var prediction = CNTKLib.SquaredError(classifierOutput, outputVariable);
TrainingParameterScheduleDouble learningRatePerSample = new TrainingParameterScheduleDouble(0.00178125, 1); //0.00178125
TrainingParameterScheduleDouble momentumTimeConstant = CNTKLib.MomentumAsTimeConstantSchedule(256);
IList <Learner> parameterLearners = new List <Learner>()
{
Learner.MomentumSGDLearner(classifierOutput.Parameters(), learningRatePerSample, momentumTimeConstant, true)
};
trainer = Trainer.CreateTrainer(classifierOutput, trainingLoss, prediction, parameterLearners);
}