Module: tf_agents.utils.tensor_normalizer

Tensor statistics and normalization.

Classes

class EMATensorNormalizer: TensorNormalizer with exponential moving avg. mean and var estimates.

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

class TensorNormalizer: Encapsulates tensor normalization and owns normalization variables.

Functions

kahan_summation(...): Calculate stable acculated sum using compensation for low-bits.

parallel_variance_calculation(...): Calculate the sufficient statistics (average & second moment) of two sets.

absolute_import Instance of __future__._Feature
division Instance of __future__._Feature
print_function Instance of __future__._Feature