tf_agents.networks.normal_projection_network.NormalProjectionNetwork

Generates a tfp.distribution.Normal by predicting a mean and std.

Inherits From: DistributionNetwork, Network

tf_agents.networks.normal_projection_network.NormalProjectionNetwork(
    sample_spec,
    activation_fn=None,
    init_means_output_factor=0.1,
    std_bias_initializer_value=0.0,
    mean_transform=tf_agents.networks.normal_projection_network.tanh_squash_to_spec,
    std_transform=tf.nn.softplus,
    state_dependent_std=False,
    scale_distribution=False,
    seed=None,
    seed_stream_class=tfp.util.SeedStream,
    name='NormalProjectionNetwork'
)

Note: By default this network uses tanh_squash_to_spec to normalize its output. Due to the nature of the tanh function, values near the spec bounds cannot be returned.

Note: The standard deviations are independent of the input.

Args
sample_spec	A tensor_spec.BoundedTensorSpec detailing the shape and dtypes of samples pulled from the output distribution.
activation_fn	Activation function to use in dense layer.
init_means_output_factor	Output factor for initializing action means weights.
std_bias_initializer_value	Initial value for the bias of the stddev_projection_layer or the direct bias_layer depending on the state_dependent_std flag.
mean_transform	Transform to apply to the calculated means. Uses tanh_squash_to_spec by default.
std_transform	Transform to apply to the stddevs.
state_dependent_std	If true, stddevs will be produced by MLP from state. else, stddevs will be an independent variable.
scale_distribution	Whether or not to use a bijector chain to scale distributions to match the sample spec. Note the TransformedDistribution does not support certain operations required by some agents or policies such as KL divergence calculations or Mode.
seed	seed used for Keras kernal initializers.
seed_stream_class	The seed stream class. This is almost always tfp.util.SeedStream, except for in unit testing, when one may want to seed all the layers deterministically.
name	A string representing name of the network.

Attributes
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.
output_spec
state_spec

Methods

copy

View source

copy(
    **kwargs
)

Create a shallow copy of this network.

Note: Network layer weights are never copied. This method recreates the Network instance with the same arguments it was initialized with (excepting any new kwargs).

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

Returns
A shallow copy of this network.

create_variables

View source

create_variables(
    input_tensor_spec=None, **kwargs
)

Force creation of the network's variables.

Return output specs.

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

Returns
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.

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

get_initial_state

View source

get_initial_state(
    batch_size=None
)

Returns an initial state usable by the network.

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

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

get_layer

View source

get_layer(
    name=None, index=None
)

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).

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

Returns
A layer instance.

Raises
ValueError	In case of invalid layer name or index.

summary

View source

summary(
    line_length=None, positions=None, print_fn=None
)

Prints a string summary of the network.

Args
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.

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