Put Near#


Action Space	`Discrete(7)`
Observation Space	`Dict('direction': Discrete(4), 'image': Box(0, 255, (7, 7, 3), uint8), 'mission': MissionSpace(<function PutNearEnv._gen_mission at 0x7f813f498af0>, [['blue', 'green', 'grey', 'purple', 'red', 'yellow'], ['key', 'ball', 'box'], ['blue', 'green', 'grey', 'purple', 'red', 'yellow'], ['key', 'ball', 'box']]))`
Reward Range	`(0, 1)`
Creation	`gymnasium.make("MiniGrid-PutNear-8x8-N3-v0")`

Description#

The agent is instructed through a textual string to pick up an object and place it next to another object. This environment is easy to solve with two objects, but difficult to solve with more, as it involves both textual understanding and spatial reasoning involving multiple objects.

Mission Space#

“put the {move_color} {move_type} near the {target_color} {target_type}”

{move_color} and {target_color} can be “red”, “green”, “blue”, “purple”, “yellow” or “grey”.

{move_type} and {target_type} Can be “box”, “ball” 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	Drop an object
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
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:

The agent picks up the wrong object.
The agent drop the correct object near the target.
Timeout (see max_steps).

Registered Configurations#

N: number of objects.

MiniGrid-PutNear-6x6-N2-v0
MiniGrid-PutNear-8x8-N3-v0