Describes a tfp.distribution.Distribution using nested parameters.
tf_agents.distributions.utils.DistributionSpecV2(
event_shape: tf.TensorShape,
dtype: tf.DType,
parameters: tf_agents.distributions.utils.Params
)
Args | |
---|---|
event_shape
|
The distribution's event_shape . This is the shape that
distribution.sample() returns. distribution.sample(sample_shape)
returns tensors of shape sample_shape + event_shape .
|
dtype
|
The distribution's dtype .
|
parameters
|
The recursive parameters of the distribution, with tensors
having directly been converted to tf.TypeSpec objects.
|
Raises | |
---|---|
TypeError
|
If for any entry x in parameters : tf.is_tensor(x) .
|
Methods
__eq__
__eq__(
other
)
Return self==value.