RandomResetWrapper

class maze.core.wrappers.random_reset_wrapper.RandomResetWrapper(*args, **kwds)

A wrapper skipping the first few steps by taking random actions. This is useful for skipping irrelevant initial parts of a trajectory or for introducing randomness in the training process.

Parameters

• env – Environment/wrapper to wrap.

• min_skip_steps – Minimum number of steps to skip.

• max_skip_steps – Maximum number of steps to skip.

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]]]

This wrapper does not modify observations and actions.

reset() → Any

Override BaseEnv.reset to reset the step count.