R²-WAM：World Action Modelのための修復・棄却ポストトレーニング
$R^2$-WAM: Repair-and-Reject Post-Training for World Action Models
映像予測モデルを「入力行動と整合する未来を予測するよう修復」し、その予測を使って劣った行動サンプルを棄却・負例微調整することで、環境との追加対話なしに方策を改善する手法。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Ruiyan Xu, Haisheng Su, Sixu Lin, Zhaokun Yue, Chengming Hu, Xin Jin, Guiliang Liu
分類: cs.RO
原文アブストラクト
World Action Models (WAMs) emerge as a promising foundation for policy refinement by predicting the consequences of sampled actions. However, visually plausible predictions can mislead policy refinement if they fail to reflect the input actions. To address this mismatch, we introduce $R^2$-WAM, a two-stage repair-and-reject post-training framework that first improves the consistency of predicted futures with input actions, then uses these futures to select inferior action samples for negative fine-tuning. The repair stage grounds imagination in observed robot behavior through a kinematic alignment score that measures agreement between predicted and demonstrated motion, enabling the predicted video to faithfully reflect its input actions. Using the repaired video model, the rejection stage compares imagined outcomes of sampled and demonstrated actions, selectively applying negative fine-tuning to samples whose predicted task progress falls below the demonstrated reference by a prescribed margin. Together, the two stages extend video prediction from representation learning to consequence-based policy refinement without additional environment interaction or changes to the inference procedure. $R^2$-WAM achieves 93.8% average success on RoboTwin 2.0 across clean and randomized settings. On the long-horizon real-world Fold Shirt task, it achieves 87.5% average success, compared with 0% for Fast-WAM.