ml: 按运行手册审查修订——头分目录不互相覆盖（ml/runs/<CFG>、selected_ckpt/CKPT）；统一 $PYTHON（Windows Git Bash 可跑）；gen 按实测样本/任务自动补量；R10 改终态判据（≥5k 样本/s≈60k 步≤3.5h）；m5 纯策略/仿真安全层双口径；无老师题定长 6 s 口径；APG 展开随批时长、端点+中点铰链、余量 3 mm（投影同步）；挖错池只用本轮；门禁加 R7；bench 加 R8 对抗集与刹停率、--nc-n/--route-n/--r8-n；新增 check_r2 与 acceptance；export 默认 fp32；出题分块防 OOM；val 为空保护

2026-10-18 06:40:24 +08:00
parent 8800a68cad
commit f8cdabb781
18 changed files with 493 additions and 156 deletions
@@ -2,7 +2,10 @@
  python -m ml.apg.apg_finetune --init ml/runs/base/best.pt --samples ml/data/samples --out ml/runs/apg [--pool ml/runs/mine/pool.jsonl]
 每条展开固定一个噪声 z（确定性可微映射）；每次推理提交 3 步（已提交前缀 3 步，与部署一致）；
 截断反传：每 seg_plans 次推理（=3·seg_plans 步）反传一次并截断状态梯度。
-损失：段末到达项 + Σ碰撞铰链 ReLU(margin_train − 间隙)（逐胶囊对）+ 平滑（速度²+加速度²）+ 行程 + BC 锚定（MeanFlow 损失）。"""
+损失：段末到达项 + Σ碰撞铰链 ReLU(margin_train − 间隙)（逐胶囊对，端点+中点）+ 平滑（速度²+加速度²）+ 行程 + BC 锚定（MeanFlow 损失）。
+2026-10-18：展开长度不再定长 60 次推理（3.6 s，会截掉老师时长 > 3.6 s 的绕远题），改为覆盖本批 exec_s p90×1.2，上限 plans_max；
+  "到达"仍是每 seg_plans 段末的距离项（无到达即停），属有意设计：段末项给出持续的接近梯度。
+  margin_train 5 → 3 mm：老师轨迹自身最小间隙 p50 4.4 / p90 5.9 mm，5 mm 会让约一半 BC 标签与碰撞项对抗；3 mm ≈ 老师 p10。"""
 import argparse, json, math, os, random, time
 import torch

@@ -45,7 +48,7 @@ def main():
    opt = torch.optim.AdamW(model.parameters(), lr=C['lr'], betas=(0.9, 0.95), weight_decay=0.0)
    amp = dev.startswith('cuda') and C.get('amp') == 'bf16'
    step = torch.tensor(STEP, device=dev)
-    log = open(os.path.join(a.out, 'log.jsonl'), 'a')
+    log = open(os.path.join(a.out, 'log.jsonl'), 'w')
    base, _ = evaluate(model.eval(), kin, val_tasks, dev)
    print('EVAL0', json.dumps(base), flush=True); log.write(json.dumps({'eval': base, 'step': 0}) + '\n')
    best = base['success']
@@ -62,9 +65,12 @@ def main():
        subs = torch.zeros(B, 2, 6, device=dev); nsub = torch.zeros(B, dtype=torch.long, device=dev); sub_t = torch.zeros(B, device=dev)
        opt.zero_grad(set_to_none=True)
        stats = {'col': 0.0, 'tgt': 0.0, 'smooth': 0.0}
-        nseg = math.ceil(C['plans'] / C['seg_plans'])
+        # 展开长度随本批任务时长：覆盖本批 exec_s 的 p90 × 1.2（无老师参考题按 6 s），夹在 [plans, plans_max]
+        exb = torch.nan_to_num(ex, nan=6.0)
+        n_plans = int(min(C['plans_max'], max(C['plans'], math.ceil(1.2 * torch.quantile(exb, 0.9).item() / (3 * 0.02)))))
+        nseg = math.ceil(n_plans / C['seg_plans'])
        seg_loss = torch.zeros((), device=dev); prev_d = torch.zeros(B, 6, device=dev)
-        for p in range(C['plans']):
+        for p in range(n_plans):
            tnow = p * 3 * 0.02
            r = queue.shape[1]
            pre = torch.zeros(B, 3, 6, device=dev); pre[:, :r] = queue[:, :r]
@@ -92,15 +98,16 @@ def main():
            for k in range(3):
                d = queue[:, k]
                qp = q; q = kin.clamp_box(q + d)
-                G = kin.gaps(q, M)
+                # 碰撞铰链：端点 + 中点（与仿真/运行时的离散检查一致）
+                G = kin.gaps(torch.cat([q, 0.5 * (q + qp)], 0), M)
                hinge = torch.relu(M - G['gap'])
-                col = torch.zeros(B, device=dev).index_add(0, G['b'], hinge)
+                col = torch.zeros(2 * B, device=dev).index_add(0, G['b'], hinge).view(2, B).sum(0)
                sm = ((d / step) ** 2).sum(-1) + (((d - prev_d) / step) ** 2).sum(-1)
                prev_d = d
                seg_loss = seg_loss + C['w_col'] * col.mean() + C['w_smooth'] * sm.mean() + C['w_len'] * d.abs().sum(-1).mean()
                stats['col'] += col.mean().item(); stats['smooth'] += sm.mean().item()
            queue = commit
-            if (p + 1) % C['seg_plans'] == 0 or p == C['plans'] - 1:
+            if (p + 1) % C['seg_plans'] == 0 or p == n_plans - 1:
                xf = kin.cum_xf(q)
                pe = kin.fk(q, xf); Rq = kin.orient(q, xf).reshape(B, 9)
                pose = (R.abs().sum(-1) > 0).float()
@@ -122,7 +129,7 @@ def main():
        opt.step()
        with torch.no_grad():
            e, oe = goal_err(kin, q, T, R)
-        rec = {'it': it, 'err_mm_mean': e.mean().item(), 'reach_frac': ((e < 1) & (oe < 0.5)).float().mean().item(), 'bc': l_bc.item(),
+        rec = {'it': it, 'plans': n_plans, 'err_mm_mean': e.mean().item(), 'reach_frac': ((e < 1) & (oe < 0.5)).float().mean().item(), 'bc': l_bc.item(),
               'gnorm': gn.item(), **stats, 'min': (time.time() - t0) / 60}
        if it % 10 == 0: print(json.dumps(rec), flush=True)
        log.write(json.dumps(rec) + '\n'); log.flush()