Go To Red Blue Ball#

Go To Red Blue Ball

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-GoToRedBlueBall-v0")

Description#

Go to the red ball or to the blue ball. There is exactly one red or blue ball, and some distractors. The distractors are guaranteed not to be red or blue balls. Language is not required to solve this level.

Mission Space#

“go to the {color} ball”

{color} is the color of the box. Can be “red” or “blue”.

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 goes to the ball.

  2. Timeout (see max_steps).

Registered Configurations#

  • BabyAI-GoToRedBlueBall-v0