| from pydantic import BaseModel |
| from typing import List, Literal |
|
|
| class Task(BaseModel): |
| """ |
| Meta Learning - Priority Panic |
| Model representing a single task in the environment. |
| """ |
| id: int |
| description: str |
| priority: Literal["low", "medium", "high"] |
| deadline: int |
| energy_cost: int |
| completed: bool |
|
|
| class Observation(BaseModel): |
| """ |
| Meta Learning - Priority Panic |
| Model representing the current observation of the environment. |
| """ |
| tasks: List[Task] |
| energy: int |
| step_count: int |
| social_debt: float |
| streak: int |
| last_action_result: str |
|
|
| class Action(BaseModel): |
| """ |
| Meta Learning - Priority Panic |
| Model representing an action taken by the agent. |
| """ |
| action_type: Literal["complete_task", "skip", "noop"] |
| task_ids: List[int] |
|
|
| class Reward(BaseModel): |
| """ |
| Meta Learning - Priority Panic |
| Model representing the reward received after an action. |
| """ |
| score: float |