114514

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"]