114514

project/policies/__init__.py

@@ -0,0 +1,5 @@
+from .high_level_ppo import HighLevelPolicy, load_high_policy
+from .low_level_ppo import LowLevelPolicy, load_low_policy
+
+__all__ = ["HighLevelPolicy", "load_high_policy",
+           "LowLevelPolicy", "load_low_policy"]

project/policies/high_level_ppo.py

@@ -0,0 +1,10 @@
+"""兼容入口：高层 MaskablePPO 推理策略。"""
+from mcm26b.hrl.policy import HighLevelPolicy
+
+
+def load_high_policy(model_path: str, *, device: str = "auto",
+                     problem: int | None = None) -> HighLevelPolicy:
+    return HighLevelPolicy(model_path, device=device, problem=problem)
+
+
+__all__ = ["HighLevelPolicy", "load_high_policy"]

project/policies/low_level_ppo.py

@@ -0,0 +1,9 @@
+"""兼容入口：低层八方向到达策略（离线导航实验）。"""
+from mcm26b.hrl.policy import LowLevelPolicy
+
+
+def load_low_policy(model_path: str, *, device: str = "auto") -> LowLevelPolicy:
+    return LowLevelPolicy(model_path, device=device)
+
+
+__all__ = ["LowLevelPolicy", "load_low_policy"]