ObservationVisualizationWrapper

class maze.core.wrappers.observation_visualization_wrapper.ObservationVisualizationWrapper(env: MazeEnv, plot_function: str | None)

An observation visualization wrapper allows to apply custom observation visualization functions which are then shown in Tensorboard.

Parameters:

• env – The environment to wrap.

• plot_function – The custom matplotlib plotting function.

clone_from(env: ObservationVisualizationWrapper) → None

(overrides SimulatedEnvMixin)

implementation of SimulatedEnvMixin.

get_observation_and_action_dicts(maze_state: Any | None, maze_action: Any | None, first_step_in_episode: bool) → Tuple[Dict[int | str, Any] | None, Dict[int | str, Any] | None]

(overrides Wrapper)

Keep both actions and observation the same.

step(action: Dict[str, int | numpy.ndarray]) → Tuple[Dict[str, numpy.ndarray], float, bool, Dict[Any, Any]]

(overrides BaseEnv)

Triggers logging events for observations, actions and reward.