There are 120 scenes in iTHOR, evenly spread across kitchens, living rooms, bedrooms, and bathrooms. The list of scenes is defined as:

kitchens = [f"FloorPlan{i}" for i in range(1, 31)]
living_rooms = [f"FloorPlan{200 + i}" for i in range(1, 31)]
bedrooms = [f"FloorPlan{300 + i}" for i in range(1, 31)]
bathrooms = [f"FloorPlan{400 + i}" for i in range(1, 31)]

scenes = kitchens + living_rooms + bedrooms + bathrooms

["FloorPlan1", "FloorPlan2", "FloorPlan3", {...}, "FloorPlan430"]

We provide a cached alias to the above definitions using the

controller.ithor_scenes(
    include_kitchens=True,
    include_living_rooms=True,
    include_bedrooms=True,
    include_bathrooms=True
)

Response

[
    "FloorPlan1",
    "FloorPlan2",
    {...},
    "FloorPlan201",
    {...},
    "FloorPlan301",
    {...},
    "FloorPlan430",
]

Parameters

include_kitchens

: bool = True

Includes the 30 kitchens (i.e., FloorPlan[1:30]) in the returned list when True.

include_living_rooms

: bool = True

Includes the 30 living rooms (i.e., FloorPlan[201:230]) in the returned list when

True

.

include_bedrooms

: bool = True

Includes the 30 bedrooms (i.e., FloorPlan[301:330]) in list when

True

include_bathrooms

: bool = True

Includes the 30 bathrooms (i.e., FloorPlan[401:430]) in list when

True

.

It is common to train agents on a subset of scenes, in order to validate and test how well they generalize to new scenes and environments. For each room type, it is standard practice to treat the first $20$ scenes as training scenes, the next $5$ scenes as validation scenes, and the last $5$ scenes as testing scenes.