提出可调时序密度的扩散规划器，提升长程决策效率与精度
Mixed-Density Diffuser: Efficient Planning with Non-Uniform Temporal Resolution
- 允许不同时间点采用不同生成密度，灵活控制规划粒度
- 在三个基准数据集上超越当前最优模型，达新SOTA性能
- 适合需要高效长程规划的强化学习任务，如机器人路径规划
近期研究显示，稀疏步长规划相比单步规划能更好捕捉长期依赖关系，且无需额外内存或计算开销。然而，过度稀疏的规划会降低性能。我们假设规划时序密度在不同阶段应非均匀分布，某些轨迹段需更密集生成。为此提出混合密度扩散规划器（MDD），其时序密度为可调超参数。实验表明，MDD在Maze2D、Franka Kitchen和Antmaze三个D4RL任务数据集上均优于当前最优框架Diffusion Veteran（DV），并创下D4RL基准新纪录。
原文摘要 · Abstract (English)
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 memory or computational cost. However, predicting excessively sparse plans degrades performance. We hypothesize this temporal density threshold is non-uniform across a planning horizon and that certain parts of a predicted trajectory should be more densely generated. We propose Mixed-Density Diffuser (MDD), a diffusion planner where the densities throughout the horizon are tunable hyperparameters. We show that MDD surpasses the SOTA Diffusion Veteran (DV) framework across the Maze2D, Franka Kitchen, and Antmaze Datasets for Deep Data-Driven Reinforcement Learning (D4RL) task domains, achieving a new SOTA on the D4RL benchmark.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。