潜在世界模型中的决策度量对齐：MPC规划的诊断与动作条件目标
Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning
AI总结：
该研究针对潜在世界模型中MPC规划的决策度量对齐问题，提出两种秩一致性诊断指标，开发DA-LeWM模型，验证其可加快收敛并提升在线成功率，改善潜在MPC的几何结构。
AI中文摘要：
JEPA风格的潜在世界模型可将目标潜在向量的欧氏距离用作模型预测控制（MPC）的代价。然而，任务变量的强解码并不能保证该特定代价能按实际任务进度对候选动作序列进行排序，我们将后者特性称为“决策度量对齐”。我们引入Plan-Real Spearman，该指标用于衡量随机规划下潜在与实际的秩一致性；还引入CEM-stage Spearman，用于衡量交叉熵方法（CEM）搜索集中提议时的相同一致性。我们分析了潜在距离能保留实际代价排序的充分条件，确定了编码器失真、终端回滚误差和候选裕度为控制量。基于观察到的经验对齐差距，DA-LeWM通过逆动力学和演示条件目标-动作头对LeWM进行增强。在所有实验中，DA-LeWM相比LeWM加快了收敛速度并取得更高的在线成功率，而探测分数保持相似。这些结果表明，动作条件目标可改善基于欧氏代价、CEM的潜在MPC所使用的几何结构。
英文摘要：
JEPA-style latent world models can use Euclidean distance to a goal latent as the cost for model-predictive control (MPC). Strong decoding of task variables, however, does not guarantee that this particular cost ranks candidate action sequences by real task progress. We call the latter property \emph{decision-metric alignment}. We introduce Plan-Real Spearman, which measures latent--real rank agreement on random plans, and CEM-stage Spearman, which measures the same agreement as cross-entropy-method (CEM) search concentrates its proposal. We analyze sufficient conditions under which latent distance preserves real-cost rankings, identifying encoder distortion, terminal rollout error, and candidate margins as the controlling quantities. Guided by the observed empirical alignment gap, DA-LeWM augments LeWM with inverse-dynamics and demonstration-conditioned goal-action heads. Across all our experiments, DA-LeWM accelerates convergence and achieves higher online success than LeWM, while probe scores remain similar. These results show that action-conditioned objectives improve the geometry used by Euclidean-cost, CEM-based latent MPC.
