multigrid.envs.locked_hallway module#
- class multigrid.envs.locked_hallway.LockedHallwayEnv[source]#
Bases:
RoomGrid
Description#
This environment consists of a hallway with multiple locked rooms on either side. To unlock each door, agents must first find the corresponding key, which may be in another locked room. Agents are rewarded for each door they unlock.
The standard setting is cooperative, where all agents receive a reward for each door that is opened.
Mission Space#
“unlock all the doors”
Observation Space#
The multi-agent observation space is a Dict mapping from agent index to corresponding agent observation space.
Each agent observation is a dictionary with the following entries:
- imagendarray[int] of shape (view_size, view_size,
WorldObj.dim) Encoding of the agent’s partially observable view of the environment, where each grid cell is encoded as a 3 dimensional tuple: (
Type,Color,State)
- imagendarray[int] of shape (view_size, view_size,
- directionint
Agent’s direction (0: right, 1: down, 2: left, 3: up)
- missionMission
Task string corresponding to the current environment configuration
Action Space#
The multi-agent action space is a Dict mapping from agent index to corresponding agent action space.
Agent actions are discrete integer values, given by:
Num
Name
Action
0
left
Turn left
1
right
Turn right
2
forward
Move forward
3
pickup
Pick up an object
4
drop
Drop an object
5
toggle
Toggle / activate an object
6
done
Done completing task
Rewards#
A reward of
1 - 0.9 * (step_count / max_steps)is given when a door is unlocked.Termination#
The episode ends if any one of the following conditions is met:
All doors are unlocked
Timeout (see
max_steps)
Registered Configurations#
MultiGrid-LockedHallway-2Rooms-v0MultiGrid-LockedHallway-4Rooms-v0MultiGrid-LockedHallway-6Rooms-v0
- __init__(num_rooms: int = 6, room_size: int = 5, max_hallway_keys: int = 1, max_keys_per_room: int = 2, max_steps: int | None = None, joint_reward: bool = True, **kwargs)[source]#
- Parameters:
- num_roomsint, default=6
Number of rooms in the environment
- room_sizeint, default=5
Width and height for each of the rooms
- max_hallway_keysint, default=1
Maximum number of keys in the hallway
- max_keys_per_roomint, default=2
Maximum number of keys in each room
- max_stepsint, optional
Maximum number of steps per episode
- joint_rewardbool, default=True
Whether all agents receive the same reward
- **kwargs