dqn.py 文件源码

def compute_weighted_value_loss(y, t, weights,
                                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.
        weights (ndarray): Weights for y, t.
        clip_delta (bool): Use the Huber loss function if set True.
        batch_accumulator (str): 'mean' will devide loss by batchsize
    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:
        losses = F.huber_loss(y, t, delta=1.0)
    else:
        losses = F.square(y - t) / 2
    losses = F.reshape(losses, (-1,))
    loss_sum = F.sum(losses * weights)
    if batch_accumulator == 'mean':
        loss = loss_sum / y.shape[0]
    elif batch_accumulator == 'sum':
        loss = loss_sum
    return loss