![]() |
TensorNormalizer with exponential moving avg. mean and var estimates.
Inherits From: TensorNormalizer
tf_agents.utils.tensor_normalizer.EMATensorNormalizer(
tensor_spec, scope='normalize_tensor', norm_update_rate=0.001
)
Attributes | |
---|---|
nested
|
True if tensor is nested, False otherwise. |
Methods
copy
copy(
scope=None
)
Copy constructor for EMATensorNormalizer.
normalize
normalize(
tensor, clip_value=5.0, center_mean=True, variance_epsilon=0.001
)
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
update(
tensor, outer_dims=(0,)
)
Updates tensor normalizer variables.