用图神经网络学习动作排序，提升规划模型泛化能力。
Graph Neural Network Based Action Ranking for Planning
- 构建含动作信息的图结构，结合GNN与GRU学习动作优先级。
- 在小规模问题训练后，成功解决大规模不可行规划任务。
- 相比传统方法，成功率与计划质量均显著提升。
我们提出一种基于学习排序的动作选择新方法，用于经典规划任务。引入一种显式捕捉动作信息的新图表示，并设计融合门控循环单元（GRU）的图神经网络（GNN）架构来学习动作排名。与需全局一致值函数的方法不同，本方法仅需局部一致的排序关系。模型在小规模可解问题生成的数据上训练，应用于计算复杂度极高的大规模实例。在标准规划基准测试中，该方法不仅对更大规模问题表现出更强泛化能力，且在成功率与计划质量上均优于多个基线方法（包括值函数与动作排序类方法）。
原文摘要 · Abstract (English)
We propose a novel approach to learn relational policies for classical planning based on learning to rank actions. We introduce a new graph representation that explicitly captures action information and propose a Graph Neural Network (GNN) architecture augmented with Gated Recurrent Units (GRUs) to learn action rankings. Unlike value-function based approaches that must learn a globally consistent function, our action ranking method only needs to learn locally consistent ranking. Our model is trained on data generated from small problem instances that are easily solved by planners and is applied to significantly larger instances where planning is computationally prohibitive. Experimental results across standard planning benchmarks demonstrate that our action-ranking approach not only achieves better generalization to larger problems than those used in training but also outperforms multiple baselines (value function and action ranking) methods in terms of success rate and plan quality.
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。