1

I am trying to define a log loss function for a multi class classification problem as:

    self.loss = tf.losses.log_loss(
        labels=self.sampled_actions,
        predictions= [self.probability[i][self.sampled_actions[i]] for i in range(tf.shape(self.sampled_actions)[0])],
        weights=self.discounted_rewards)

Here, self.sampled_actions is a 1D tensor of 0/1/2 (e.g: [0,1,2,1,0,2]) which corresponds to which action is the ground truth. self.probability is defined as:

    h = tf.layers.dense(
        self.observations,
        units=hidden_layer_size,
        activation=tf.nn.relu,
        kernel_initializer=tf.contrib.layers.xavier_initializer())

    self.probability = tf.layers.dense(
        h,
        units=3,
        activation=tf.sigmoid,
        kernel_initializer=tf.contrib.layers.xavier_initializer())

As the probabilities of all three actions, 0,1,2 for any given observation in the input.

However, when I run this program, I get the error: 

Traceback (most recent call last):
  File "spaceinvaders.py", line 68, in <module>
    hidden_layer_size, learning_rate, checkpoints_dir='checkpoints')
  File "/home/elfarouk/Desktop/opengym/policy_network_space_invaders.py", line 49, in __init__
    predictions= [self.probability[i][self.sampled_actions[i]] for i in range(tf.shape(self.sampled_actions)[0])],
TypeError: range() integer end argument expected, got Tensor.

Is there a way to specify that my prediction in the loss function should be dependent on the sampled_actions?

AspiringMat
  • 2,161
  • 2
  • 21
  • 33
  • tf.shape() will return you a tensor object and saddly you cannot iterate over a tensor. see https://stackoverflow.com/questions/39446313/using-tf-unpack-when-first-dimension-of-variable-is-none?noredirect=1&lq=1 – J.Zagdoun Aug 16 '18 at 09:37

0 Answers0