/// <summary>
/// θの初期値を取得
/// </summary>
/// <returns></returns>
public MatrixUtil GetInitialThetaMatrix()
{
MatrixUtil matrix = MatrixUtil.Arange(fieldSize * fieldSize, actionNum);
for (int state = 0; state < matrix.shape[0]; state++)
{
for (int action = 0; action < matrix.shape[1]; action++)
{
int i = state % fieldSize;
int j = state / fieldSize;
switch (action)
{
case 0:
matrix.Set(state, action, activeLines_line[i, j + 1] ? 0 : 1);
break;
case 1:
matrix.Set(state, action, activeLines_row[i + 1, j] ? 0 : 1);
break;
case 2:
matrix.Set(state, action, activeLines_line[i, j] ? 0 : 1);
break;
case 3:
matrix.Set(state, action, activeLines_row[i, j] ? 0 : 1);
break;
}
}
}
return(matrix);
}
public void Init(MainModel model, int fieldSize, MatrixUtil initialTheta)
{
this.model = model;
this.fieldSize = fieldSize;
this.eta = this.model.eta;
this.gamma = this.model.gamma;
this.epsilon = this.model.epsilon;
this.shrinkRate = this.model.shrinkRate;
this.episodeMax = this.model.episodeMax;
this.limit = this.model.limit;
this.stateNum = initialTheta.shape[0];
this.actionNum = initialTheta.shape[1];
r = new System.Random();
Q = MatrixUtil.Arange(stateNum, actionNum);
MatrixUtil.UniFuncArangeAll(Q, () => (float)(r.NextDouble()));
Q = Q.Multiply(initialTheta);
}
