世界建模在机器人动作学习中究竟改善了哪些方面？
研究对FastWAM与OpenWAM做受控的未来视频预测损失消融，固定模型架构、初始化、机器人训练数据与训练步数。在已见任务的干净条件下，预测监督分别将成功率提升24.38和72.91个百分点；轨迹聚类显示多个粗粒度轨迹簇内成功率更高，部分簇频率变化很小，说明增益不只来自轨迹模式分布变化。但在分布偏移下增益不稳定：未见任务上的提升因模型和任务而异，两种模型在环境随机化下成功率均偏低，预测监督无一致优势。作者还将未来视频预测作为π0.5的辅助训练目标，仅训练时使用的轻量Transformer预测器把成功率从82.94%提升到89.19%。
发布于 10-27 12:56来源：arXiv cs.RO
转载 · 官方发布原文：arXiv cs.RO ·《What Does World Modeling Actually Improve in Robot Action Learning?》查看原链
arXiv:2610.34593v1 Announce Type: new Abstract: World Action Models (WAMs) combine future-video prediction with robot action learning, yet improvements in task success alone do not reveal how predictive supervision manifests in execution behavior or whether its benefits persist under task and environmental shifts. We conduct controlled future-video prediction loss ablations within FastWAM and OpenWAM, keeping model architecture, initialization, robot training data, and training steps fixed within each model family.
Under clean conditions on seen tasks, predictive supervision increases success rates by 24.38 and 72.91 percentage points, respectively. Trajectory clustering further reveals higher success rates within several coarse trajectory clusters, including cases where cluster frequencies change little, indicating that the gains are not solely reflected in changes in the prevalence of trajectory patterns.
However, these benefits do not consistently persist under distribution shifts: improvements on unseen tasks vary across models and tasks, while both models exhibit low success rates under the evaluated environmental randomizations, without a consistent advantage from predictive supervision. We further introduce future-video prediction as an auxiliary training objective for $\pi_{0.5}$, where a lightweight Transformer predictor used only during training increases success from 82.94% to 89.19%. These findings support future-video prediction as effective auxiliary supervision for action learning, while distinguishing improved execution on familiar tasks from reliable transfer and showing that such gains need not rely on a large pretrained video diffusion transformer (DiT) in the evaluated setting.