Files
Robot_Arm/ml/mining/loop.sh
T
Hark 2a0a2e55ad ml: 数据生成 + 可微运动学对拍 + MeanFlow/WTA 策略与闭环仿真 + APG/挖错/ONNX 导出与运行手册
- M1 数据生成器:采样/老师/距离下界认证/时间律/统计/一致性门禁;确定性老师(碰撞次数计时 + resetSession)、pos 任务冻结 J6、--consensus 邻域共识过滤、Dr 类。
- 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/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。
2026-10-18 06:40:23 +08:00

30 lines
1.8 KiB
Bash
Executable File

#!/usr/bin/env bash
# 后训练主循环(方案 §7):APG 首轮 → 挖错 3–6 轮(每轮:挖错 → [E2 老师补路径] → APG 微调 → 门禁/回滚)
# bash ml/mining/loop.sh [轮数=6] [每轮 APG 步数=1000] [每轮出题数=50000]
set -e
cd "$(dirname "$0")/../.."
ROUNDS=${1:-6}; STEPS=${2:-1000}; N=${3:-50000}
mkdir -p ml/runs/mine
[ -f ml/runs/gate_tasks.jsonl ] || python -m ml.mining.mine_round --make-gate 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
for ((r=1; r<=ROUNDS; r++)); do
D=ml/runs/mine/r$r; mkdir -p $D
python -m ml.mining.mine_round --ckpt ml/runs/current.pt --seed $((1000+r)) --n $N --out $D
# E2(局部极小)请老师补少量路径(唯一保留的后训练老师用途)
if [ -s $D/e2_tasks.jsonl ]; then
node ml/gen/gen_dataset.cjs --tasks $D/e2_tasks.jsonl --seed $((5000+r)) --out ml/data/e2/shard_e2_r$r.jsonl
node ml/prep/build_dataset.cjs ml/data/e2/shard_e2_r$r.jsonl ml/data/samples_e2
SAMPLES="ml/data/samples ml/data/samples_e2"
fi
POOLS=$(ls ml/runs/mine/r*/pool.jsonl)
python -m ml.apg.apg_finetune --init ml/runs/current.pt --samples $SAMPLES --pool $POOLS --out ml/runs/apg_r$r --steps $STEPS
python -m ml.mining.gate --old ml/runs/current.pt --new ml/runs/apg_r$r/best.pt --tasks ml/runs/gate_tasks.jsonl --out $D/gate.json $FIXED
FIXED="--fixed $D/gate_fixed.jsonl"
gain=$(python -c "import json;print(json.load(open('$D/gate.json'))['gain_pp'])")
echo "round $r gain ${gain} pp"
if python -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
done
echo "最终模型:ml/runs/current.pt"