Recent studies demonstrate that diffusion planners benefit from sparse-step planning over single-step planning. Training models to skip steps in their trajectories helps capture long-term dependencies without additional or memory computational cost. However, predicting excessively sparse plans degrades performance. We hypothesize this temporal density threshold is non-uniform across a temporal horizon and that certain parts of a planned trajectory should be more densely planned. We propose Mixed-Density Diffuser (MDD), a diffusion planner where the densities throughout the horizon are tunable hyperparameters. We show that MDD achieves a new SOTA across the Maze2D, Franka Kitchen, and Antmaze D4RL task domains.

翻译：近期研究表明，扩散规划器通过稀疏步长规划相较于单步规划具有优势。训练模型跳过轨迹中的某些步骤有助于捕捉长期依赖关系，而无需增加计算或内存成本。然而，预测过度稀疏的规划会降低性能。我们假设这种时间密度阈值在时间范围内是非均匀的，且规划轨迹的某些部分应进行更密集的规划。为此，我们提出混合密度扩散器（Mixed-Density Diffuser, MDD），这是一种扩散规划器，其整个时间范围内的密度是可调超参数。实验证明，MDD在Maze2D、Franka Kitchen和Antmaze D4RL任务域中均实现了新的最优性能。