提出LoMAP方法，让扩散模型生成更安全的长程轨迹。
Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning
- 从离线数据中学习低秩子空间，引导采样不偏离可行轨迹
- 在长程规划任务中显著减少不可行轨迹，提升生成可靠性
- 无需训练，可无缝集成到现有扩散规划器中
基于扩散的生成建模在利用离线数据解决长程稀疏奖励任务方面展现出巨大潜力。尽管取得一定进展，其可靠性仍不稳定，主要因采样过程中存在随机风险，导致生成不可行轨迹，限制其在安全关键场景的应用。本文发现失败主因是采样时引导不准，并推导出引导误差的下界，证明了流形偏差的存在。为此，提出无需训练的局部流形近似与投影（LoMAP）方法：将引导样本投影到由离线数据近似的低秩子空间上，避免生成不可行轨迹。在标准离线强化学习基准上验证该方法，涵盖具有挑战性的长程规划任务。进一步表明，作为独立模块，LoMAP可融入层次化扩散规划器，带来性能提升。
原文摘要 · Abstract (English)
Recent advances in diffusion-based generative modeling have demonstrated significant promise in tackling long-horizon, sparse-reward tasks by leveraging offline datasets. While these approaches have achieved promising results, their reliability remains inconsistent due to the inherent stochastic risk of producing infeasible trajectories, limiting their applicability in safety-critical applications. We identify that the primary cause of these failures is inaccurate guidance during the sampling procedure, and demonstrate the existence of manifold deviation by deriving a lower bound on the guidance gap. To address this challenge, we propose Local Manifold Approximation and Projection (LoMAP), a training-free method that projects the guided sample onto a low-rank subspace approximated from offline datasets, preventing infeasible trajectory generation. We validate our approach on standard offline reinforcement learning benchmarks that involve challenging long-horizon planning. Furthermore, we show that, as a standalone module, LoMAP can be incorporated into the hierarchical diffusion planner, providing further performance enhancements.
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。