Network Outputting Expected Value and Variance of Rewards.

Inherits From: Network

input_tensor_spec A nest of tensor_spec.TensorSpec representing the input observations.
action_spec A nest of tensor_spec.BoundedTensorSpec representing the actions.
preprocessing_layers (Optional.) A nest of tf.keras.layers.Layer representing preprocessing for the different observations. All of these layers must not be already built. For more details see the documentation of networks.EncodingNetwork.
preprocessing_combiner (Optional.) A keras layer that takes a flat list of tensors and combines them. Good options include tf.keras.layers.Add and tf.keras.layers.Concatenate(axis=-1). This layer must not be already built. For more details see the documentation of networks.EncodingNetwork.
conv_layer_params Optional list of convolution layers parameters, where each item is a length-three tuple indicating (filters, kernel_size, stride).
fc_layer_params Optional list of fully_connected parameters, where each item is the number of units in the layer.
dropout_layer_params Optional list of dropout layer parameters, where each item is the fraction of input units to drop. The dropout layers are interleaved with the fully connected layers; there is a dropout layer after each fully connected layer, except if the entry in the list is None. This list must have the same length of fc_layer_params, or be None.
activation_fn Activation function, e.g. tf.keras.activations.relu.
kernel_initializer Initializer to use for the kernels of the conv and dense layers. If none is provided a default variance_scaling_initializer
batch_squash If True the outer_ranks of the observation are squashed into the batch dimension. This allow encoding networks to be used with observations with shape [BxTx...].
min_variance Float. The minimum allowed predicted variance. Predicted variances less than this value will be clipped to this value.
max_variance Float. The maximum allowed predicted variance. Predicted variances greater than this value will be clipped to this value.
dtype The dtype to use by the convolution and fully connected layers.
name A string representing the name of the network.

ValueError If input_tensor_spec contains more than one observation. Or if action_spec contains more than one action.

input_tensor_spec Returns the spec of the input to the network of type InputSpec.
layers Get the list of all (nested) sub-layers used in this Network.



View source

Create a shallow copy of this network.

**kwargs Args to override when recreating this network. Commonly overridden args include 'name'.

A shallow copy of this network.


View source

Force creation of the network's variables.

Return output specs.

input_tensor_spec (Optional). Override or provide an input tensor spec when creating variables.
**kwargs Other arguments to, e.g. training=True.

Output specs - a nested spec calculated from the outputs (excluding any batch dimensions). If any of the output elements is a tfp Distribution, the associated spec entry returned is a DistributionSpec.

ValueError If no input_tensor_spec is provided, and the network did not provide one during construction.


View source

Returns an initial state usable by the network.

batch_size Tensor or constant: size of the batch dimension. Can be None in which case not dimensions gets added.

A nested object of type self.state_spec containing properly initialized Tensors.


View source

Retrieves a layer based on either its name (unique) or index.

If name and index are both provided, index will take precedence. Indices are based on order of horizontal graph traversal (bottom-up).

name String, name of layer.
index Integer, index of layer.

A layer instance.

ValueError In case of invalid layer name or index.


View source

Prints a string summary of the network.

line_length Total length of printed lines (e.g. set this to adapt the display to different terminal window sizes).
positions Relative or absolute positions of log elements in each line. If not provided, defaults to [.33, .55, .67, 1.].
print_fn Print function to use. Defaults to print. It will be called on each line of the summary. You can set it to a custom function in order to capture the string summary.

ValueError if summary() is called before the model is built.