无需先验知识，自动发现环境对称性并学习解耦表征
Disentangled Representation Learning through Unsupervised Symmetry Group Discovery
- 智能体通过与环境互动，无监督发现动作空间的群结构
- 在三个不同对称结构环境中均超越现有解耦方法
- 适合对解耦表示学习感兴趣的研究人员
基于对称性的解耦表征学习利用环境变换的群结构来揭示变化的潜在因素。先前的方法需要对对称群结构有强先验知识，或对子群性质施加严格假设。本文提出一种新方法：让具身智能体通过与环境的无监督交互，自主发现其动作空间的群结构。我们在最小假设下证明了真实对称群分解的可识别性，并推导出两个算法：一个用于从交互数据中发现群分解，另一个用于学习线性对称性解耦（LSBD）表征，且无需假设特定子群性质。该方法在三个具有不同群分解特性的环境中验证，性能优于现有LSBD方法。
原文摘要 · Abstract (English)
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.
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。