fix(train): 首次正式预训练（21850 步闭环到达 0%）排查后修正——FK/平滑改加在配对去噪估计上（原加在随机噪声一步采样上=回归条件均值，多峰塌成单峰，实测候选标准差 0.030/幅度 0.151）；时间嵌入最高角频率 1000→50、MF 分支 fp32、p_neq 前 5000 步为 0（实测 du/dt 均方根 6–12 vs v 1.1）；增广 40%/3°/12 步收回；新增 dagger 阶段（策略闭环状态请老师重规划 ×2 轮微调）；开训前老师轨迹回放自检；评估加开环误差与候选多样性，best/早停按到达率+开环误差

ml/mining/loop.sh

@@ -12,13 +12,14 @@ ROUNDS=${1:-6}; STEPS=${2:-1000}; N=${3:-50000}
 mkdir -p ml/runs/mine
 [ -f ml/runs/gate_tasks.jsonl ] || $PY -m ml.mining.mine_round --make-gate ${MINE_GATE_N:-2000} --seed 777 --out ml/runs
 [ -f ml/runs/current.pt ] || cp ml/runs/apg/best.pt ml/runs/current.pt
-SAMPLES="ml/data/samples"; FIXED=""; small=0
+BASE_S="ml/data/samples $(ls -d ml/data/samples_dag_* 2>/dev/null | tr '\n' ' ')"   # 2026-10-18：BC 正则也用 DAgger 样本
+SAMPLES="$BASE_S"; FIXED=""; small=0
 for ((r=1; r<=ROUNDS; r++)); do
   D=ml/runs/mine/r$r; mkdir -p $D
   if [ -f $D/gate.json ]; then
     gain=$($PY -c "import json;print(json.load(open('$D/gate.json'))['gain_pp'])")
     echo "round $r 已完成（gain ${gain} pp），跳过"; FIXED="--fixed $D/gate_fixed.jsonl"
-    [ -s ml/data/e2/shard_e2_r$r.jsonl ] && SAMPLES="ml/data/samples ml/data/samples_e2"
+    [ -s ml/data/e2/shard_e2_r$r.jsonl ] && SAMPLES="$BASE_S ml/data/samples_e2"
     if $PY -c "import sys;sys.exit(0 if $gain < 0.5 else 1)"; then small=$((small+1)); else small=0; fi
     if [ $small -ge 2 ]; then echo "连续 2 轮提升 < 0.5 pp，停止"; break; fi
     continue
@@ -35,7 +36,7 @@ for ((r=1; r<=ROUNDS; r++)); do
   if [ -s $D/e2_tasks.jsonl ]; then
     [ -f $E2F ] || { node ml/gen/gen_dataset.cjs --tasks $D/e2_tasks.jsonl --seed $((5000+r)) --out $E2F.part && mv $E2F.part $E2F; }
     node ml/prep/build_dataset.cjs ml/data/e2/shard_e2_r$r.jsonl ml/data/samples_e2
-    SAMPLES="ml/data/samples ml/data/samples_e2"
+    SAMPLES="$BASE_S ml/data/samples_e2"
   fi
   res=""; [ -f ml/runs/apg_r$r/last.pt ] && res="--resume ml/runs/apg_r$r/last.pt"
   $PY -m ml.apg.apg_finetune --init ml/runs/current.pt --samples $SAMPLES --pool $D/pool.jsonl --out ml/runs/apg_r$r --steps $STEPS $res