TensorFlow：“ValueError:没有为任何变量提供渐变”

Question

我在tensorflow中实现了DeepMind的DQN算法，并在我调用optimizer.minimize(self.loss)的行中遇到了这个错误：

ValueError: No gradients provided for any variable...

通过阅读有关此错误的其他文章，我发现这意味着损失函数不依赖于用于建立模型的任何张量，但在我的代码中，我无法看出这是怎么回事。qloss()函数显然依赖于对predict()函数的调用，该调用依赖于所有的层张量来进行计算。

模型设置代码可以在这里查看。

Answer 1

我发现问题是，在我的qloss()函数中，我从张量中提取值，对它们进行操作并返回值。虽然值确实依赖于张量，但它们并不是封装在张量中的，因此TensorFlow无法判断它们依赖于图中的张量。

我通过更改qloss()来修正这个问题，这样它就可以直接对张量进行操作，并返回一个张量。以下是新功能：

def qloss(actions, rewards, target_Qs, pred_Qs):
    """
    Q-function loss with target freezing - the difference between the observed
    Q value, taking into account the recently received r (while holding future
    Qs at target) and the predicted Q value the agent had for (s, a) at the time
    of the update.

    Params:
    actions   - The action for each experience in the minibatch
    rewards   - The reward for each experience in the minibatch
    target_Qs - The target Q value from s' for each experience in the minibatch
    pred_Qs   - The Q values predicted by the model network

    Returns: 
    A list with the Q-function loss for each experience clipped from [-1, 1] 
    and squared.
    """
    ys = rewards + DISCOUNT * target_Qs

    #For each list of pred_Qs in the batch, we want the pred Q for the action
    #at that experience. So we create 2D list of indeces [experience#, action#]
    #to filter the pred_Qs tensor.
    gather_is = tf.squeeze(np.dstack([tf.range(BATCH_SIZE), actions]))
    action_Qs = tf.gather_nd(pred_Qs, gather_is)

    losses = ys - action_Qs
    clipped_squared_losses = tf.square(tf.minimum(tf.abs(losses), 1))

    return clipped_squared_losses