用无监督图特征提升搜索新颖性判断，避免对称状态重复探索
Symmetry-Invariant Novelty Heuristics via Unsupervised Weisfeiler-Leman Features
- 用无监督的韦斯费勒-莱曼特征替代原子检测新颖性
- 在经典规划与难解基准上表现优于传统方法
- 适合需要高效搜索的通用规划任务
新颖性启发式通过探索具有新原子的状态来辅助启发式搜索。然而，现有方法不具备对称不变性，可能导致冗余探索。本文初步提出使用无监督的韦斯费勒-莱曼特征（WLFs）代替原子来检测新颖性。WLFs 是近期用于学习通用规划问题领域相关启发式的特征。我们探索其在合成提升型、领域无关的新颖性启发式中的应用，该方法对对称状态保持不变性。在国际规划竞赛和难解实例基准测试集上的实验表明，基于 WLFs 合成的新颖性启发式取得了有前景的结果。
原文摘要 · Abstract (English)
Novelty heuristics aid heuristic search by exploring states that exhibit novel atoms. However, novelty heuristics are not symmetry invariant and hence may sometimes lead to redundant exploration. In this preliminary report, we propose to use Weisfeiler-Leman Features for planning (WLFs) in place of atoms for detecting novelty. WLFs are recently introduced features for learning domain-dependent heuristics for generalised planning problems. We explore an unsupervised usage of WLFs for synthesising lifted, domain-independent novelty heuristics that are invariant to symmetric states. Experiments on the classical International Planning Competition and Hard To Ground benchmark suites yield promising results for novelty heuristics synthesised from WLFs.
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。