ml: 全流程代码与运行手册（数据打包/可微运动学与对拍/MeanFlow+WTA 模型/训练/闭环仿真/APG/挖错循环/ONNX 导出）；webapp 策略运行时 ik-policy.js + ?policy=1 接入；tests/policy_bench.cjs；ik-solver 增 pairList/clusterExport/criticalPairs/pairGap/leverTable

ml/configs/apg.json

@@ -0,0 +1,10 @@
+{
+  "apg": {
+    "batch": 128, "lr": 1e-4, "steps": 3000, "grad_clip": 1.0, "amp": "bf16",
+    "plans": 60, "seg_plans": 10,
+    "margin_train_mm": 5.0,
+    "w_tgt": 1.0, "w_rot": 0.3, "w_col": 2.0, "w_smooth": 0.02, "w_len": 0.001, "w_bc": 0.5,
+    "cat_weights": {"A": 0.4, "B": 1.0, "C": 1.6, "D": 0.6, "Dr": 0.6},
+    "eval_every": 500, "eval_tasks": 512
+  }
+}

ml/configs/base.json

@@ -0,0 +1,10 @@
+{
+  "model": {"d": 192, "heads": 8, "ff": 768, "enc": 4, "dec": 4},
+  "train": {
+    "batch": 1024, "lr": 1e-3, "warmup": 1000, "steps": 60000, "wd": 0.01, "betas": [0.9, 0.95],
+    "amp": "bf16", "grad_clip": 1.0,
+    "w_mf": 1.0, "w_fk": 0.5, "w_smooth": 0.05, "w_value": 0.1, "w_sub": 0.1,
+    "p_neq": 0.25, "fk_caps": 96,
+    "eval_every": 2000, "eval_tasks": 512, "log_every": 50, "patience_evals": 5
+  }
+}

ml/configs/wta.json

@@ -0,0 +1,10 @@
+{
+  "model": {"d": 192, "heads": 8, "ff": 768, "enc": 4, "dec": 4, "head": "wta", "K": 8},
+  "train": {
+    "batch": 1024, "lr": 1e-3, "warmup": 1000, "steps": 60000, "wd": 0.01, "betas": [0.9, 0.95],
+    "amp": "bf16", "grad_clip": 1.0,
+    "w_mf": 1.0, "w_fk": 0.5, "w_smooth": 0.05, "w_value": 0.1, "w_sub": 0.1,
+    "p_neq": 0.25, "fk_caps": 96,
+    "eval_every": 2000, "eval_tasks": 512, "log_every": 50, "patience_evals": 5
+  }
+}