Locked Room

Action Space	Discrete(7)
Observation Space	Dict('direction': Discrete(4), 'image': Box(0, 255, (7, 7, 3), uint8), 'mission': MissionSpace(<function LockedRoomEnv._gen_mission at 0x7f813f48e1f0>, [['blue', 'green', 'grey', 'purple', 'red', 'yellow'], ['blue', 'green', 'grey', 'purple', 'red', 'yellow'], ['blue', 'green', 'grey', 'purple', 'red', 'yellow']]))
Reward Range	(0, 1)
Creation	gymnasium.make("MiniGrid-LockedRoom-v0")

Description

The environment has six rooms, one of which is locked. The agent receives a textual mission string as input, telling it which room to go to in order to get the key that opens the locked room. It then has to go into the locked room in order to reach the final goal. This environment is extremely difficult to solve with vanilla reinforcement learning alone.

Mission Space

“get the {lockedroom_color} key from the {keyroom_color} room, unlock the {door_color} door and go to the goal”

{lockedroom_color}, {keyroom_color}, and {door_color} can be “red”, “green”, “blue”, “purple”, “yellow” or “grey”.

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	Toggle/activate an object
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

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 reaches the goal.

2. Timeout (see max_steps).

Registered Configurations

• MiniGrid-LockedRoom-v0