用图神经网络提升规划搜索效率并识别对称性，显著改进了学习型规划器性能。
Learning Efficiency Meets Symmetry Breaking
- 构建图结构表示规划问题，兼顾学习效率与对称性检测能力
- 提出动作剪枝与状态剪枝两种方法，在最新IPC数据集上超越LAMA
- 适合研究智能规划、自动化推理及学习型搜索算法的开发者
基于图神经网络的学习型规划器可学习适用于大搜索空间的搜索引导，但其在处理对称性方面的潜力尚未充分探索。本文提出一种规划问题的图表示方法，兼顾学习效率与对称性检测能力，并设计了动作剪枝和状态剪枝两种剪枝策略以在搜索过程中管理对称性。将这些技术集成到Fast Downward后，在最新IPC学习赛道数据集上首次实现对LAMA的超越。代码已开源：https://github.com/bybeye/Distincter。
原文摘要 · Abstract (English)
Learning-based planners leveraging Graph Neural Networks can learn search guidance applicable to large search spaces, yet their potential to address symmetries remains largely unexplored. In this paper, we introduce a graph representation of planning problems allying learning efficiency with the ability to detect symmetries, along with two pruning methods, action pruning and state pruning, designed to manage symmetries during search. The integration of these techniques into Fast Downward achieves a first-time success over LAMA on the latest IPC learning track dataset. Code is released at: https://github.com/bybeye/Distincter.
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。