发表机构
Princeton University; Torc Robotics（普林斯顿大学; Torc Robotics）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
EpicWorldModel提出基于流匹配的随机JEPA框架，在部分可观测环境中利用预测方差引导CEM规划，平衡目标达成与遮挡区域探索，成功率最高提升22%。
AI 中文摘要
基于联合嵌入预测架构（JEPA）的潜在世界模型在设计上是确定性的。虽然在完全可观测场景中表现良好，但当过去的观测和行动导致多种合理的未来可能性时（例如由于遮挡），这种范式会失效。我们引入了EpicWorldModel，一个用于在部分可观测性下训练随机JEPA以应对具有内在不确定性的环境和任务的框架。我们将EpicWorldModel的预测器与其潜在表示空间联合训练，在目标相关场景内容缺失于条件历史中时，使用流匹配目标直接预测多个潜在的未来状态。我们表明，流预测方差（其动机源于其与预测熵上界的关系）可作为规划中有用的探索指导。通过将此不确定性信号纳入基于交叉熵方法（CEM）的规划中，我们的方法在实现目标的同时，平衡了对最可能隐藏遮挡目标的未知区域的探索。我们通过一系列潜在规划实验展示了EpicWorldModel的有效性，其在各项任务中表现最佳或与最佳持平，成功率相比LeWorldModel实现了高达22%的经验提升。
英文摘要
Latent world models based on Joint-Embedding Predictive Architecture (JEPA) are deterministic by design. While successful in fully observable scenarios, this paradigm breaks down when past observations and actions lead to multiple plausible future possibilities, e.g., due to occlusion. We introduce EpicWorldModel, a framework to train stochastic JEPAs for environments and tasks with inherent uncertainty under partially observability. We jointly train the EpicWorldModel predictor with its latent representation space to directly predict multiple potential future states using a flow-matching objective, when the goal-relevant scene content is absent from the conditioning history. We show that flow predictive variance, motivated by its relation to an upper bound on predictive entropy, serves as a useful exploration guidance for planning. By incorporating this uncertainty signal into Cross-Entropy Method (CEM)-based planning, our approach balances goal-reaching with exploration of uncertain regions where occluded goals are most likely to be located. We demonstrate the effectiveness of EpicWorldModel through a series of latent planning experiments with the best or on-par performance across tasks, showing up to 22% empirical improvement in success rate over LeWorldModel.
CommentsAccepted at NeurIPS 2026. 18 pages, 8 figures, 5 tables (11 pages main text, 4 pages appendix)
