MazeEnvMonitoringWrapper

class maze.core.wrappers.monitoring_wrapper.MazeEnvMonitoringWrapper(*args, **kwds)

A MazeEnv monitoring wrapper logging events for observations, actions and rewards.

Parameters

• env – The environment to wrap.

• observation_logging – If True observation events are logged.

• action_logging – If True action events are logged.

• reward_logging – If True additional reward events are logged.

clone_from(env: maze.core.wrappers.monitoring_wrapper.MazeEnvMonitoringWrapper) → 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)

Keep both actions and observation the same.

reset() → Dict[str, numpy.ndarray]

(overrides BaseEnv)

Resets the wrapper and returns the initial observation.

return

the initial observation after resetting.

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

(overrides BaseEnv)

Triggers logging events for observations, actions and reward.