class maze.core.wrappers.sorted_spaces_wrapper.SortedSpacesWrapper(*args, **kwds)

This class wraps a given StructuredEnvSpacesMixin env to ensure that all observation- and action-spaces are sorted alphabetically. This is required that Maze custom action distributions and observation processing are in line with RLLib’s internal processing pipeline.

property action_space

(overrides StructuredEnvSpacesMixin)

The currently active gym action space.

clone_from(env: maze.core.wrappers.sorted_spaces_wrapper.SortedSpacesWrapper)None

(overrides SimulatedEnvMixin)

implementation of SimulatedEnvMixin.

get_observation_and_action_dicts(maze_state: Optional[Any], maze_action: Optional[Any], first_step_in_episode: bool) → Tuple[Optional[Dict[Union[int, str], Any]], Optional[Dict[Union[int, str], Any]]]

(overrides Wrapper)

This wrapper does not modify observations and actions.

property observation_space

(overrides StructuredEnvSpacesMixin)

Keep this env compatible with the gym interface by returning the

observation space of the current policy.