diag: H 段（老师 oracle 走 rollout / 前缀消融 / 子目标越过顶点规则 / 分轴与分类别指标）；训练：EMA、选模不落在 p_neq 预热、闭环分数选模、24000 步余弦、p_neq 0.5 + p_edge 0.1、子目标头切断抄输入、前缀/dq 增广；仿真：last 记真正提交的候选、碰撞与到达按每题时限、回放门禁读 pass+指纹并走 rollout；数据：动作标签按 1.25·STEP 归一化（act_scale 随 meta/ckpt/ONNX 传递，旧模型 1.0）、收回亏空结转、DAgger 带 qPrev 与起步速度、打包签名变更自动重打；ik-policy.js 同步（actScale、子目标规则、DLS 时清 lastPlan）；本机执行清单与 README 更新

ml/mining/gate.py

@@ -12,8 +12,8 @@ from ml.sim.closed_loop import evaluate
 
 
 def load(path, dev):
-    ck = torch.load(path, map_location=dev)
-    m = build(ck['cfg']).to(dev); m.load_state_dict(ck['model']); return m.eval()
+    from ml.common.ckpt import load_policy      # 2026-10-19：EMA 权重 + act_scale
+    return load_policy(path, dev)[0]
 
 
 def per_task_success(pers):

ml/mining/mine_round.py

@@ -28,8 +28,8 @@ def main():
         with open(os.path.join(a.out, a.name), 'w') as f:
             for t in ts: f.write(json.dumps(t) + '\n')
         print('gate tasks', len(ts)); return
-    ck = torch.load(a.ckpt, map_location=a.device)
-    model = build(ck['cfg']).to(a.device); model.load_state_dict(ck['model']); model.eval()
+    from ml.common.ckpt import load_policy      # 2026-10-19：EMA 权重 + act_scale
+    model, ck = load_policy(a.ckpt, a.device)
     tasks = sample_tasks(kin, a.n, a.seed)
     g = torch.Generator(); g.manual_seed(a.seed)
     cls = {k: [] for k in ('E1', 'E2', 'E3', 'E4', 'E5', 'ok')}