alfworld-goal-interpreter

1# Goal Interpretation Protocol
2 
3## 1. Parse the Task Statement
4When a new task is assigned, immediately analyze the natural language instruction to extract its core components. Use the parsing script (`parse_goal.py`) to perform this analysis.
5 
6**Input:** The raw task string (e.g., "look at pillow under the desklamp").
7**Output:** A structured dictionary containing:
8- `primary_target`: The main object to interact with.
9- `reference_object`: The object that defines a location or condition.
10- `spatial_relation`: The preposition linking them (e.g., under, on, in).
11- `action`: The verb defining the required interaction.
12 
13## 2. Generate Sub-Objectives
14Based on the parsed components, formulate a clear, sequential plan. The plan must account for the spatial relationship.
15 
16**Example Logic:**
17- **IF** relation is `under` → Sub-goal 1: Locate the `reference_object`. Sub-goal 2: Inspect the area beneath it for the `primary_target`.
18- **IF** relation is `in` or `on` → Sub-goal 1: Locate the `reference_object`. Sub-goal 2: Check its contents/surface.
19 
20## 3. Identify Required Objects & Actions
21Map the parsed objects to the available action types in the environment. The primary action verbs (look, take, use, etc.) from the task must be translated into the agent's available action set (go to, take, use, etc.).
22 
23**Critical Check:** If the `reference_object` is a container (drawer, fridge), ensure the plan includes the `open` action before inspection.
24 
25## 4. Execute & Adapt
26…