dqn.py 文件源码

def compute_value_loss(y, t, clip_delta=True, batch_accumulator='mean'):
    """Compute a loss for value prediction problem.

    Args:
        y (Variable or ndarray): Predicted values.
        t (Variable or ndarray): Target values.
        clip_delta (bool): Use the Huber loss function if set True.
        batch_accumulator (str): 'mean' or 'sum'. 'mean' will use the mean of
            the loss values in a batch. 'sum' will use the sum.
    Returns:
        (Variable) scalar loss
    """
    assert batch_accumulator in ('mean', 'sum')
    y = F.reshape(y, (-1, 1))
    t = F.reshape(t, (-1, 1))
    if clip_delta:
        loss_sum = F.sum(F.huber_loss(y, t, delta=1.0))
        if batch_accumulator == 'mean':
            loss = loss_sum / y.shape[0]
        elif batch_accumulator == 'sum':
            loss = loss_sum
    else:
        loss_mean = F.mean_squared_error(y, t) / 2
        if batch_accumulator == 'mean':
            loss = loss_mean
        elif batch_accumulator == 'sum':
            loss = loss_mean * y.shape[0]
    return loss