|View source on GitHub|
Instances of this class represent how sampling is reparameterized.
tf.compat.v1.distributions.ReparameterizationType( rep_type )
Two static instances exist in the distributions library, signifying one of two possible properties for samples from a distribution:
FULLY_REPARAMETERIZED: Samples from the distribution are fully
reparameterized, and straight-through gradients are supported.
NOT_REPARAMETERIZED: Samples from the distribution are not fully
reparameterized, and straight-through gradients are either partially
unsupported or are not supported at all. In this case, for purposes of
e.g. RL or variational inference, it is generally safest to wrap the
sample results in a
stop_gradients call and use policy
gradients / surrogate loss instead.
__eq__( other )
Determine if this
ReparameterizationType is equal to another.
Since RepaparameterizationType instances are constant static global instances, equality checks if two instances' id() values are equal.
other: Object to compare against.
self is other.