Environment

GridEngineEnv adapts a world factory to Gymnasium. The default action space has seven actions: up, down, left, right, use key, pick up, and wait.

Image observations contain an RGBA array plus structured info. Symbolic observations are returned by setting observation_type="grid".

from grid_engine.env import Action, GridEngineEnv
from grid_engine.examples.maze import generate

env = GridEngineEnv(initial_state_fn=generate, width=7, height=7, seed=1)
obs, info = env.reset()
obs, reward, terminated, truncated, info = env.step(Action.RIGHT)

Bases: Env[ImageObservation | GridObservation, integer]

Gymnasium Env implementation for the Grid Engine.

Create a new environment instance.

Parameters:

Name	Type	Description	Default
render_mode	str	"rgb_array" to return PIL image frames, "human" to open a window.	'rgb_array'
render_resolution	int	Width (pixels) of rendered image (height derived).	DEFAULT_RESOLUTION
render_image_map	ImageMap	Mapping of (appearance_name, properties) to asset paths.	DEFAULT_IMAGE_MAP
initial_state_fn	Callable[..., World]	Callable returning an initial World.	required
**kwargs	Any	Forwarded to initial_state_fn (e.g., size, densities, seed).	{}

grid_observation property

Return the current symbolic grid observation.

render(mode=None)

Render the current state.

Parameters:

Name	Type	Description	Default
mode	str | None	"human" to display, "rgb_array" to return PIL image. Defaults to the instance's configured render mode.	None

reset(*, seed=None, options=None)

Start a new episode.

Parameters:

Name	Type	Description	Default
seed	int | None	Override the procedural seed passed to the state factory.	None
options	dict | None	Gymnasium options (unused).	None

Returns:

Type	Description
tuple[ImageObservation | GridObservation, dict[str, object]]	Tuple[ImageObservation, dict]: ImageObservation dict and empty info dict per Gymnasium API.

state_info()

Return structured info sub-dict used in observations.

step(action)

Apply one environment step.

Parameters:

Name	Type	Description	Default
action	int | integer | Action	Integer index (or Action enum member) selecting an action from the discrete action space.	required

Returns:

Type	Description
tuple[ImageObservation | GridObservation, float, bool, bool, dict[str, object]]	Tuple[ImageObservation, float, bool, bool, dict]: (observation, reward, terminated, truncated, info).

Bases: TypedDict

Top‑level observation returned by the environment.

image: RGBA image array (H x W x 4, dtype=uint8) info: Published world/entity state.

Bases: TypedDict