Gym-MiniGrid/minigrid/envs/babyai/pickup.py

"""
Copied and adapted from https://github.com/mila-iqia/babyai.
Levels described in the Baby AI ICLR 2019 submission, with the `Pick up` instruction.
"""

from __future__ import annotations

from minigrid.envs.babyai.core.levelgen import LevelGen
from minigrid.envs.babyai.core.roomgrid_level import RejectSampling, RoomGridLevel
from minigrid.envs.babyai.core.verifier import ObjDesc, PickupInstr


class Pickup(RoomGridLevel):
    """

    ## Description

    Pick up an object, the object may be in another room.

    ## Mission Space

    "pick up a {color} {type}"

    {color} is the color of the box. Can be "red", "green", "blue", "purple",
    "yellow" or "grey".

    {type} is the type of the object. Can be "ball", "box" or "key".

    ## Action Space

    | Num | Name         | Action            |
    |-----|--------------|-------------------|
    | 0   | left         | Turn left         |
    | 1   | right        | Turn right        |
    | 2   | forward      | Move forward      |
    | 3   | pickup       | Pick up an object |
    | 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](minigrid/core/constants.py)
    - `STATE` refers to the door state with 0=open, 1=closed and 2=locked

    ## 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:

    1. The agent picks up the object.
    2. Timeout (see `max_steps`).

    ## Registered Configurations

    - `BabyAI-Pickup-v0`

    """

    def gen_mission(self):
        self.place_agent()
        self.connect_all()
        objs = self.add_distractors(num_distractors=18, all_unique=False)
        self.check_objs_reachable()
        obj = self._rand_elem(objs)
        self.instrs = PickupInstr(ObjDesc(obj.type, obj.color))


class UnblockPickup(RoomGridLevel):
    """

    ## Description

    Pick up an object, the object may be in another room. The path may
    be blocked by one or more obstructors.

    ## Mission Space

    "pick up a/the {color} {type}"

    {color} is the color of the box. Can be "red", "green", "blue", "purple",
    "yellow" or "grey".

    {type} is the type of the object. Can be "ball", "box" or "key".

    ## Action Space

    | Num | Name         | Action            |
    |-----|--------------|-------------------|
    | 0   | left         | Turn left         |
    | 1   | right        | Turn right        |
    | 2   | forward      | Move forward      |
    | 3   | pickup       | Pick up an object |
    | 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](minigrid/core/constants.py)
    - `STATE` refers to the door state with 0=open, 1=closed and 2=locked

    ## 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:

    1. The agent picks up the object.
    2. Timeout (see `max_steps`).

    ## Registered Configurations

    - `BabyAI-UnblockPickup-v0`

    """

    def gen_mission(self):
        self.place_agent()
        self.connect_all()
        objs = self.add_distractors(num_distractors=20, all_unique=False)

        # Ensure that at least one object is not reachable without unblocking
        # Note: the selected object will still be reachable most of the time
        if self.check_objs_reachable(raise_exc=False):
            raise RejectSampling("all objects reachable")

        obj = self._rand_elem(objs)
        self.instrs = PickupInstr(ObjDesc(obj.type, obj.color))


class PickupLoc(LevelGen):
    """

    ## Description

    Pick up an object which may be described using its location. This is a
    single room environment.

    Competencies: PickUp, Loc. No unblocking.

    ## Mission Space

    "pick up the {color} {type}"

    {color} is the color of the box. Can be "red", "green", "blue", "purple",
    "yellow" or "grey".

    {type} is the type of the object. Can be "ball", "box" or "key".

    ## Action Space

    | Num | Name         | Action            |
    |-----|--------------|-------------------|
    | 0   | left         | Turn left         |
    | 1   | right        | Turn right        |
    | 2   | forward      | Move forward      |
    | 3   | pickup       | Pick up an object |
    | 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](minigrid/core/constants.py)
    - `STATE` refers to the door state with 0=open, 1=closed and 2=locked

    ## 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:

    1. The agent picks up the object.
    2. Timeout (see `max_steps`).

    ## Registered Configurations

    - `BabyAI-PickupLoc-v0`

    """

    def __init__(self, **kwargs):
        # We add many distractors to increase the probability
        # of ambiguous locations within the same room
        super().__init__(
            action_kinds=["pickup"],
            instr_kinds=["action"],
            num_rows=1,
            num_cols=1,
            num_dists=8,
            locked_room_prob=0,
            locations=True,
            unblocking=False,
            **kwargs,
        )


class PickupDist(RoomGridLevel):
    """

    ## Description

    Pick up an object
    The object to pick up is given by its type only, or
    by its color, or by its type and color.
    (in the current room, with distractors)

    ## Mission Space

    "pick up a/the {color}/{type}/{color}{type}"

    {color} is the color of the box. Can be "red", "green", "blue", "purple",
    "yellow" or "grey".

    {type} is the type of the object. Can be "ball", "box" or "key".

    ## Action Space

    | Num | Name         | Action            |
    |-----|--------------|-------------------|
    | 0   | left         | Turn left         |
    | 1   | right        | Turn right        |
    | 2   | forward      | Move forward      |
    | 3   | pickup       | Pick up an object |
    | 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](minigrid/core/constants.py)
    - `STATE` refers to the door state with 0=open, 1=closed and 2=locked

    ## 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:

    1. The agent picks up the object.
    2. Timeout (see `max_steps`).

    ## Registered Configurations

    - `BabyAI-PickupDist-v0`
    - `BabyAI-PickupDistDebug-v0`

    """

    def __init__(self, debug=False, **kwargs):
        self.debug = debug
        super().__init__(num_rows=1, num_cols=1, room_size=7, **kwargs)

    def gen_mission(self):
        # Add 5 random objects in the room
        objs = self.add_distractors(num_distractors=5)
        self.place_agent(0, 0)
        obj = self._rand_elem(objs)
        type = obj.type
        color = obj.color

        select_by = self._rand_elem(["type", "color", "both"])
        if select_by == "color":
            type = None
        elif select_by == "type":
            color = None

        self.instrs = PickupInstr(ObjDesc(type, color), strict=self.debug)


class PickupAbove(RoomGridLevel):
    """

    ## Description

    Pick up an object (in the room above)
    This task requires to use the compass to be solved effectively.

    ## Mission Space

    "go to the {color} {type}"

    {color} is the color of the box. Can be "red", "green", "blue", "purple",
    "yellow" or "grey".

    {type} is the type of the object. Can be "ball", "box" or "key".

    ## Action Space

    | Num | Name         | Action            |
    |-----|--------------|-------------------|
    | 0   | left         | Turn left         |
    | 1   | right        | Turn right        |
    | 2   | forward      | Move forward      |
    | 3   | pickup       | Pick up an object |
    | 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](minigrid/core/constants.py)
    - `STATE` refers to the door state with 0=open, 1=closed and 2=locked

    ## 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:

    1. The agent picks up the object.
    2. Timeout (see `max_steps`).

    ## Registered Configurations

    - `BabyAI-PickupAbove-v0`

    """

    def __init__(self, max_steps: int | None = None, **kwargs):
        room_size = 6
        if max_steps is None:
            max_steps = 8 * room_size**2

        super().__init__(room_size=room_size, max_steps=max_steps, **kwargs)

    def gen_mission(self):
        # Add a random object to the top-middle room
        obj, pos = self.add_object(1, 0)
        # Make sure the two rooms are directly connected
        self.add_door(1, 1, 3, locked=False)
        self.place_agent(1, 1)
        self.connect_all()

        self.instrs = PickupInstr(ObjDesc(obj.type, obj.color))