基于扩散的简单分层规划
Simple Hierarchical Planning with Diffusion
AI总结：
本文提出 Hierarchical Diffuser，一种结合分层与扩散规划优势的简单高效方法，通过高层跳跃式规划降低计算成本并扩大感受野，低层子目标引导微调，在离线强化学习基准上显著提升了训练与规划速度及组合分布外任务的泛化能力。
摘要：
基于扩散的生成方法已被证明在利用离线数据集建模轨迹方面是有效的。然而，它们经常面临计算挑战，并且在泛化能力上可能会表现不佳，特别是在为长时程任务捕捉时间抽象方面。为了克服这一点，我们引入了 Hierarchical Diffuser，这是一种结合了分层规划和基于扩散规划优势的简单、快速却出奇有效的规划方法。我们的模型在较高层级采用了一种“跳跃式”规划策略，这使其能够拥有更大的感受野，同时计算成本更低——正如我们通过经验验证的那样，这对于基于扩散的规划方法是一个关键因素。此外，跳跃式子目标引导我们的低层规划器，促进了微调阶段并进一步提升了我们方法的有效性。我们在标准的离线强化学习基准上进行了经验评估，结果表明，与非分层的 Diffuser 以及其他分层规划方法相比，我们的方法在训练和规划速度方面具有卓越的性能和效率。此外，我们探索了模型的泛化能力，特别是我们的方法如何提升在组合性分布外任务上的泛化能力。
英文摘要：
Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets. However, they often face computational challenges and can falter in generalization, especially in capturing temporal abstractions for long-horizon tasks. To overcome this, we introduce the Hierarchical Diffuser, a simple, fast, yet surprisingly effective planning method combining the advantages of hierarchical and diffusion-based planning. Our model adopts a "jumpy" planning strategy at the higher level, which allows it to have a larger receptive field but at a lower computational cost -- a crucial factor for diffusion-based planning methods, as we have empirically verified. Additionally, the jumpy sub-goals guide our low-level planner, facilitating a fine-tuning stage and further improving our approach's effectiveness. We conducted empirical evaluations on standard offline reinforcement learning benchmarks, demonstrating our method's superior performance and efficiency in terms of training and planning speed compared to the non-hierarchical Diffuser as well as other hierarchical planning methods. Moreover, we explore our model's generalization capability, particularly on how our method improves generalization capabilities on compositional out-of-distribution tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
