Lava Gap#
Action Space |
|
Observation Space |
|
Reward Range |
|
Creation |
|
Description#
The agent has to reach the green goal square at the opposite corner of the room, and must pass through a narrow gap in a vertical strip of deadly lava. Touching the lava terminate the episode with a zero reward. This environment is useful for studying safety and safe exploration.
Mission Space#
Depending on the obstacle_type
parameter:
Lava
: “avoid the lava and get to the green goal square”otherwise: “find the opening and get to the green goal square”
Action Space#
Num |
Name |
Action |
---|---|---|
0 |
left |
Turn left |
1 |
right |
Turn right |
2 |
forward |
Move forward |
3 |
pickup |
Unused |
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
andCOLOR_TO_IDX
mapping can be found in minigrid/core/constants.pySTATE
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 reaches the goal.
The agent falls into lava.
Timeout (see
max_steps
).
Registered Configurations#
S: size of map SxS.
MiniGrid-LavaGapS5-v0
MiniGrid-LavaGapS6-v0
MiniGrid-LavaGapS7-v0