A tensor_spec.BoundedTensorSpec detailing the shape and
dtypes of samples pulled from the output distribution.
Activation function to use in dense layer.
Output factor for initializing action means
Initial value for the bias of the
stddev_projection_layer or the direct bias_layer depending on the
Transform to apply to the calculated means. Uses
tanh_squash_to_spec by default.
Transform to apply to the stddevs.
If true, stddevs will be produced by MLP from state.
else, stddevs will be an independent variable.
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 used for Keras kernal initializers.
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.
A string representing name of the network.
Returns the spec of the input to the network of type InputSpec.
Get the list of all (nested) sub-layers used in this Network.
(Optional). Override or provide an input tensor spec
when creating variables.
Other arguments to network.call(), 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.
If no input_tensor_spec is provided, and the network did
not provide one during construction.