用流匹配保持动作多样性，提升隐空间策略学习效果。
LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching
- 采用流匹配学习隐动作，避免行为克隆导致的分布坍缩。
- 实验显示成功率最高提升15%，推理开销低于1倍。
- 适合需要高多样性动作策略的机器人模仿学习任务。
从大规模无标注视频中学习高质量隐动作，并结合有限的真实交互数据训练动作解码器，已成为可扩展隐策略学习的有前景范式。然而，现有方法多依赖行为克隆，易将固有的多模态动作分布坍缩为单模态，破坏预训练隐动作结构。虽然流匹配提供了潜在替代方案，但直接应用会导致动作解码阶段隐动作与物理动作失配，因学习策略具有随机性。为此，我们提出隐动作流匹配策略（LAFP），利用流匹配进行隐策略学习，并引入推理时插值机制以缓解随机性引起的失配。实验表明，LAFP在下游模仿学习任务中持续优于先前方法，成功率最高提升10-15%，且推理开销低于1倍。
原文摘要 · Abstract (English)
Learning high-quality latent actions from large-scale unlabeled videos, coupled with limited real-world interaction data for training an action decoder, has emerged as a promising paradigm for scalable latent policy learning. However, existing approaches typically rely on behavior cloning, which tends to collapse inherently multimodal action distributions into unimodal ones, thereby degrading the pretrained latent action structure. While flow matching provides a potential alternative, directly applying it leads to a misalignment between latent actions and physical actions during action decoder training, due to the stochastic nature of the learned policy. To address these, we propose Latent Action Flow Policy (LAFP), which leverages flow matching for latent policy learning and introduces an inference-time interpolation mechanism to mitigate stochasticity-induced misalignment. Experimental results demonstrate that LAFP consistently outperforms prior methods on downstream imitation learning tasks, achieving up to 10-15% improvement in success rate while incurring less than 1x additional inference overhead.
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。