ObservationNormalizationWrapper¶
- class maze.core.wrappers.observation_normalization.observation_normalization_wrapper.ObservationNormalizationWrapper(env: MazeEnv, default_strategy: str | ObservationNormalizationStrategy, default_strategy_config: Dict[str, Any], default_statistics: Dict[str, Any] | None, statistics_dump: str, sampling_policy: omegaconf.DictConfig | Policy, exclude: List[str] | None, manual_config: Dict[str | int, Dict[str, Any]] | None)¶
An observation normalization wrapper. It provides functionality for:
normalizing observations according to specified normalization strategies
clipping observations according to specified min and max values
estimating normalization statistics from observations collecting by interacting with the environment
manually overwriting the observation normalization parameters
The current implementation assumes that observation space is always a Dict (even if just a Dict-wrapped Box).
- Parameters:
env – Environment/wrapper to wrap.
default_strategy – The default observation normalization strategy.
default_statistics – Manual default normalization statistics.
statistics_dump – Path to a pickle file dump of normalization statistics.
sampling_policy – The sampling policy for estimating the statistics.
exclude – List of observation keys to exclude from normalization.
manual_config – Additional manual configuration options.
- clone_from(env: ObservationNormalizationWrapper) None¶
(overrides
SimulatedEnvMixin)implementation of
SimulatedEnvMixin.
- estimate_statistics() None¶
Estimates and sets the observation statistics from collected observations.
- get_statistics() Dict[str, Dict[str, numpy.ndarray | float | int | Iterable[float | int]]]¶
Returns the normalization statistics of the respective normalization strategy. :return: The normalization statistics for all sub steps and all dictionary observations.
- observation(observation: Any) Any¶
(overrides
ObservationWrapper)Collect observations for statistics computation or normalize them.
- param observation:
The observation to be normalized.
- return:
The normalized observation.
- classmethod register_new_observation_normalization_strategy(containing_submodule: Any)¶
Registers a new observation normalization strategy.
- Parameters:
containing_submodule – Add all classes implementing ObservationNormalizationStrategy by walking the module recursively.
- seed(seed: Any) None¶
(overrides
StructuredEnv)Apply seed to wrappers rng, and pass the seed forward to the env