tf_agents.utils.tensor_normalizer.EMATensorNormalizer

View source on GitHub

TensorNormalizer with exponential moving avg. mean and var estimates.

Inherits From: TensorNormalizer

name Returns the name of this module as passed or determined in the ctor.

name_scope Returns a tf.name_scope instance for this class.
nested True if tensor is nested, False otherwise.
submodules Sequence of all sub-modules.

Submodules are modules which are properties of this module, or found as properties of modules which are properties of this module (and so on).

a = tf.Module()
b = tf.Module()
c = tf.Module()
a.b = b
b.c = c
list(a.submodules) == [b, c]
True
list(b.submodules) == [c]
True
list(c.submodules) == []
True

trainable_variables Sequence of trainable variables owned by this module and its submodules.

variables Returns a tuple of tf variables owned by this EMATensorNormalizer.

Methods

copy

View source

Copy constructor for EMATensorNormalizer.

normalize

View source

Applies normalization to tensor.

Args
tensor Tensor to normalize.
clip_value Clips normalized observations between +/- this value if clip_value > 0, otherwise does not apply clipping.
center_mean If true, subtracts off mean from normalized tensor.
variance_epsilon Epsilon to avoid division by zero in normalization.

Returns
normalized_tensor Tensor after applying normalization.

update

View source

Updates tensor normalizer variables.

with_name_scope

Decorator to automatically enter the module name scope.

class MyModule(tf.Module):
  @tf.Module.with_name_scope
  def __call__(self, x):
    if not hasattr(self, 'w'):
      self.w = tf.Variable(tf.random.normal([x.shape[1], 3]))
    return tf.matmul(x, self.w)

Using the above module would produce tf.Variables and tf.Tensors whose names included the module name:

mod = MyModule()
mod(tf.ones([1, 2]))
<tf.Tensor: shape=(1, 3), dtype=float32, numpy=..., dtype=float32)>
mod.w
<tf.Variable 'my_module/Variable:0' shape=(2, 3) dtype=float32,
numpy=..., dtype=float32)>

Args
method The method to wrap.

Returns
The original method wrapped such that it enters the module's name scope.