Go To Seq#
 
| Action Space | 
 | 
| Observation Space | 
 | 
| Reward Range | 
 | 
| Creation | 
 | 
Description#
Sequencing of go-to-object commands.
Competencies: Maze, GoTo, Seq No locked room. No locations. No unblocking.
Mission Space#
“go to a/the {color} {type}” + “and go to a/the {color} {type}” + “, then go to a/the {color} {type}” + “and go to a/the {color} {type}”
{color} is the color of the box. Can be “red”, “green”, “blue”, “purple”, “yellow” or “grey”.
{type} is the type of the object. Can be “ball”, “box” or “key”.
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_IDXand- COLOR_TO_IDXmapping can be found in minigrid/core/constants.py
- STATErefers 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 goes to the object. 
- Timeout (see - max_steps).
Registered Configurations#
- BabyAI-GoToSeq-v0
- BabyAI-GoToSeqS5R2-v0