One Room#
Action Space |
|
Observation Space |
|
Reward Range |
|
Creation |
|
Description#
Pick up the ball. Rooms have a size of 8.
Mission Space#
“pick up the ball”
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_IDXandCOLOR_TO_IDXmapping can be found in minigrid/core/constants.pySTATErefers 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 ball.
Timeout (see
max_steps).
Registered Configurations#
BabyAI-OneRoomS8-v0BabyAI-OneRoomS12-v0BabyAI-OneRoomS16-v0BabyAI-OneRoomS20-v0