AUTOGENERATED: DO NOT EDIT FILE DIRECTLY
The agent is randomly placed within a room with one red and one blue door facing opposite directions. The agent has to open the red door and then open the blue door, in that order. Note that, surprisingly, this environment is solvable without memory.
"open the red door then the blue door"
Num | Name | Action |
---|---|---|
0 | left | Turn left |
1 | right | Turn right |
2 | forward | Move forward |
3 | pickup | Unused |
4 | drop | Unused |
5 | toggle | Toggle/activate an object |
6 | done | Unused |
(OBJECT_IDX, COLOR_IDX, STATE)
OBJECT_TO_IDX
and COLOR_TO_IDX
mapping can be found in
minigrid/minigrid.pySTATE
refers to the door state with 0=open, 1=closed and 2=lockedA reward of '1' is given for success, and '0' for failure.
The episode ends if any one of the following conditions is met:
max_steps
).MiniGrid-RedBlueDoors-6x6-v0
MiniGrid-RedBlueDoors-8x8-v0