WFC Dungeon Maze Scaled¶


Action Space	`Discrete(7)`
Observation Space	`Dict('direction': Discrete(4), 'image': Box(0, 255, (7, 7, 3), uint8), 'mission': MissionSpace(<function WFCEnv._gen_mission at 0x7f69ee06bc40>, None))`
Creation	`gymnasium.make("MiniGrid-WFC-DungeonMazeScaled-v0")`

Description¶

This environment procedurally generates a level using the Wave Function Collapse algorithm. The DungeonMazeScaled preset learns from a scaled dungeon-maze pattern to create larger repeating corridor structures.

See WFC module page for sample images of the available presets.

Requires the optional dependencies imageio and networkx to be installed with pip install minigrid[wfc].

WFC Preset¶


Preset	`DungeonMazeScaled`
Registered by default	Yes
Requires additional registration	No
Slow preset	No

Registration¶

This preset is registered by default and can be created directly with gymnasium.make("MiniGrid-WFC-DungeonMazeScaled-v0").

Generation Notes¶

This preset is intended to generate in under a minute.

Mission Space¶

“traverse the maze to get to the goal”

Action Space¶

Num	Name	Action
0	left	Turn left
1	right	Turn right
2	forward	Move forward
3	pickup	Unused
4	drop	Unused
5	toggle	Unused
6	done	Unused

Observation Encoding¶

Each tile is encoded as a 3 dimensional tuple: (OBJECT_IDX, COLOR_IDX, STATE)
OBJECT_TO_IDX and COLOR_TO_IDX mapping can be found in minigrid/core/constants.py
STATE refers to the door state with 0=open, 1=closed and 2=locked (unused)

Rewards¶

A reward of ‘1 - 0.9 * (step_count / max_steps)’ is given for success, and ‘0’ for failure.

Termination¶

The episode ends if any one of the following conditions is met:

The agent reaches the goal.
Timeout (see max_steps).

Research¶

Adapted for Minigrid by the following work.

@inproceedings{garcin2024dred,
  title = {DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design},
  author = {Garcin, Samuel and Doran, James and Guo, Shangmin and Lucas, Christopher G and Albrecht, Stefano V},
  booktitle = {Forty-first International Conference on Machine Learning},
  year = {2024},
}