學習折疊：LeHome挑戰賽2026獲獎解決方案（線上第一名，線下第二名）

摘要

我描述了我對LeHome挑戰2026（ICRA 2026的雙臂衣物折疊競賽）的解決方案。該系統在線上（模擬）輪次中，於62支隊伍中獲得第一名，並在真實世界決賽中獲得第二名。該方案透過強化學習循環改進了視覺-語言-動作策略。該策略本身即為其價值函數：同一網絡不僅預測動作，還預測成功與進度，以及若干與任務相關的未來量，而這些預測用於驅動優勢估計、即時故障檢測和候選項選擇。這項工作主要將現有的強化學習思路與工程及優化貢獻重新組合，可作為一套完整方案整體使用，亦可單獨採用：將AWR與RECAP結合應用於流匹配VLA；透過HuggingFace Hub實現異步分佈式訓練/回放管線；利用Thompson抽樣進行推理時的超參數優化；以及一套模擬到真實的配方，包含相機對齊工具、大量數據增強及類似DAgger的人機協作數據收集。

English

I describe my solution to the LeHome Challenge 2026, an ICRA 2026 competition on bimanual garment folding. The system placed 1st of 62 teams in the online (simulation) round and 2nd in the real-world final. It improves a vision-language-action (VLA) policy with a reinforcement-learning loop. The policy is its own value function: the same network that predicts actions also predicts success, progress, and a few task-relevant future quantities, and those predictions drive advantage estimation, live failure detection, and candidate selection. The work mostly recombines existing RL ideas with engineering and optimization contributions that can be used together as one recipe or individually: AWR + RECAP combined for flow-matching VLA; an asynchronous distributed training / rollout pipeline through HuggingFace Hub; inference-time hyperparameters optimization via Thompson sampling; a sim-to-real recipe with camera-alignment tooling, heavy augmentation and DAgger-like HIL data collection.