MeanZeroStdOneObservationNormalizationStrategy

class maze.core.wrappers.observation_normalization.normalization_strategies.mean_zero_std_one.MeanZeroStdOneObservationNormalizationStrategy(observation_space: gymnasium.spaces.Box, clip_range: Tuple[float | int, float | int], axis: int | Tuple[int] | List[int] | None)

Normalizes observations to have zero mean and standard deviation one.

The strategy first subtracts the observation mean followed by a division with the standard deviation. Depending on the original distribution of the input observations this yields a standard Normal.

estimate_stats(observations: List[numpy.ndarray]) → Dict[str, numpy.ndarray | float | int | Iterable[float | int]]

(overrides ObservationNormalizationStrategy)

Implementation of

ObservationNormalizationStrategy interface.

normalize_value(value: numpy.ndarray) → numpy.ndarray

(overrides ObservationNormalizationStrategy)

Implementation of

ObservationNormalizationStrategy interface.