tf_agents.utils.tensor_normalizer.StreamingTensorNormalizer

Normalizes mean & variance based on full history of tensor values.

Inherits From: TensorNormalizer

tensor_spec The specs of the tensors to normalize.
scope Scope for the tf.Module.

Methods

map_dtype

View source

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.

reset

View source

Reset the count, mean and variance to its initial state.

update

View source

Updates tensor normalizer variables.