tf_agents.utils.tensor_normalizer.EMATensorNormalizer

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
)

nested True if tensor is nested, False otherwise.

Methods

copy

View source

copy(
    scope=None
)

Copy constructor for EMATensorNormalizer.

normalize

View source

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

View source

update(
    tensor, outer_dims=(0,)
)

Updates tensor normalizer variables.