arXiv：cs.LG· Youngjoon Jeong, Jihwan Yu, Minsoo Jo, Junha Chun, Taesup Kim·· 16 小时前
PoLAR：在机器人策略学习的潜在动作中分解幅度与模式
PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning
AI 导读
PoLAR 通过在潜在动作上施加径向-方向结构，让半径编码变化的幅度、方向保留变化的模式，从而帮助下游策略将潜在动作映射为机器人动作。该方法以观测间的时间偏移作为幅度弱代理，并在双曲空间中实例化该结构。在任务内与大规模预训练设置下，PoLAR 在仿真和真实机器人实验中均优于潜在动作基线及强预训练 VLA 模型。
正文
Abstract:Robot actions vary in both extent and mode: how much change they produce and what kind of change they produce. A latent action space that reflects this structure may make it easier for downstream policies to map latent actions to robot actions. However, existing latent action methods typically rely on visual reconstruction from observation pairs without explicitly encouraging such structure. We introduce Polar Latent Actions with Radial structure (PoLAR), which imposes a radial-direction structure on latent actions, encouraging radius to encode transition extent and direction to retain transition mode. PoLAR uses temporal offsets between observations as a weak proxy for transition extent, encouraging transitions with larger offsets to occupy larger radii. We instantiate this structure in hyperbolic space, whose expanding volume with radius offers a natural fit for more diverse transition modes at larger extents. Across in-task and large-scale pretraining settings, PoLAR improves downstream policy performance in simulation and real-world robot experiments, outperforming latent action baselines and strong pretrained VLAs. These results suggest that structuring latent actions by extent and mode helps transfer visual pretraining to robot policy learning.
| Comments: | Project Page: this https URL, Accepted to CoRL 2026 |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2606.21139 [cs.RO] |
| (or arXiv:2606.21139v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2606.21139 arXiv-issued DOI via DataCite |
Submission history
From: Youngjoon Jeong [view email]
[v1]
Fri, 19 Jun 2026 06:24:05 UTC (27,068 KB)
[v2]
Wed, 14 Oct 2026 12:18:57 UTC (28,100 KB)
来源：arXiv：cs.LG · arxiv.org