AI Agents 相关度: 8/10

Disentangled Representation Learning through Unsupervised Symmetry Group Discovery

Dang-Nhu Barthélémy, Annabi Louis, Argentieri Sylvain
arXiv: 2603.11790v1 发布: 2026-03-12 更新: 2026-03-12

AI 摘要

提出一种无监督对称群发现方法,用于学习解耦表示,无需先验知识。

主要贡献

  • 提出无监督发现环境变换对称群结构的方法
  • 证明最小假设下真实对称群分解的可辨识性
  • 无需特定子群属性即可学习线性对称解耦表示的算法

方法论

通过智能体与环境交互,自主发现动作空间的群结构,并基于此学习解耦表示。

原文摘要

Symmetry-based disentangled representation learning leverages the group structure of environment transformations to uncover the latent factors of variation. Prior approaches to symmetry-based disentanglement have required strong prior knowledge of the symmetry group's structure, or restrictive assumptions about the subgroup properties. In this work, we remove these constraints by proposing a method whereby an embodied agent autonomously discovers the group structure of its action space through unsupervised interaction with the environment. We prove the identifiability of the true symmetry group decomposition under minimal assumptions, and derive two algorithms: one for discovering the group decomposition from interaction data, and another for learning Linear Symmetry-Based Disentangled (LSBD) representations without assuming specific subgroup properties. Our method is validated on three environments exhibiting different group decompositions, where it outperforms existing LSBD approaches.

标签

解耦表示学习 对称群发现 无监督学习 强化学习

arXiv 分类

cs.LG