WFC Skew2¶


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-Skew2-v0")`

Description¶

This environment procedurally generates a level using the Wave Function Collapse algorithm. The Skew2 preset learns from a skewed pattern to create asymmetric cave-like layouts with angled wall contours.

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	`Skew2`
Registered by default	No
Requires additional registration	Yes
Slow preset	No

Registration¶

This preset is not registered by default. Register the additional WFC preset group before creating it.

import gymnasium
from minigrid.envs.wfc.config import WFC_PRESETS_INCONSISTENT, register_wfc_presets

register_wfc_presets(WFC_PRESETS_INCONSISTENT, gymnasium.register)

Generation Notes¶

This preset is not marked as slow, but it can require many attempts to generate a consistent level.

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},
}