Files
2026-09-11 21:00:39 +08:00

23 lines
937 B
Python

"""兼容入口:本地简化训练环境。
HierarchicalEnv 是高层宏动作环境;LowLevelEnv 是独立八方向导航环境。
本文件不复制实现,只转发 mcm26b.hrl 下的真实类。
"""
from mcm26b.hrl.hierarchical_env import HRLReward, HierarchicalEnv
from mcm26b.hrl.low_level_env import LowLevelEnv
__all__ = ["HierarchicalEnv", "LowLevelEnv", "HRLReward", "make_local_env"]
def make_local_env(*, problem: int = 3, stage: int = 4, seed: int | None = None,
fidelity: str = "production"):
"""按题目 Prompt 的四阶段编号创建训练环境。"""
from mcm26b.hrl.curriculum import STAGES
if not 1 <= int(stage) <= len(STAGES):
raise ValueError(f"stage 必须在 1..{len(STAGES)}")
env = HierarchicalEnv(problem=problem, stage=STAGES[int(stage) - 1],
fidelity=fidelity)
if seed is not None:
env.reset(seed=seed)
return env