door_key.md 1.6 KB
AUTOGENERATED: DO NOT EDIT FILE DIRECTLY
title: Door Key
Door Key
Description
This environment has a key that the agent must pick up in order to unlock a goal and then get to the green goal square. This environment is difficult, because of the sparse reward, to solve using classical RL algorithms. It is useful to experiment with curiosity or curriculum learning.
Mission Space
"use the key to open the door and then get to the goal"
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 | Toggle/activate an object |
| 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/minigrid.pySTATErefers to the door state with 0=open, 1=closed and 2=locked
Rewards
A reward of '1' 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.
- Timeout (see
max_steps).
Registered Configurations
MiniGrid-DoorKey-5x5-v0MiniGrid-DoorKey-6x6-v0MiniGrid-DoorKey-8x8-v0MiniGrid-DoorKey-16x16-v0