Pickup Dist

Action Space	Discrete(7)
Observation Space	Dict('direction': Discrete(4), 'image': Box(0, 255, (7, 7, 3), uint8), 'mission': MissionSpace(<function BabyAIMissionSpace._gen_mission at 0x7f813d9da940>, None))
Reward Range	(0, 1)
Creation	gymnasium.make("BabyAI-PickupDistDebug-v0")

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

• 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