go_to_door.md 1.6 KB


AUTOGENERATED: DO NOT EDIT FILE DIRECTLY

title: Go To Door

Go To Door

Description

This environment is a room with four doors, one on each wall. The agent receives a textual (mission) string as input, telling it which door to go to, (eg: "go to the red door"). It receives a positive reward for performing the done action next to the correct door, as indicated in the mission string.

Mission Space

"go to the {color} door"

{color} is the color of the door. Can be "red", "green", "blue", "purple", "yellow" or "grey".

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 Done completing task

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/minigrid.py
  • STATE refers 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:

  1. The agent stands next the correct door performing the done action.
  2. Timeout (see max_steps).

Registered Configurations

  • MiniGrid-GoToDoor-5x5-v0
  • MiniGrid-GoToDoor-6x6-v0
  • MiniGrid-GoToDoor-8x8-v0