Abstract
Generalized planning using deep reinforcement learning (RL) combined with graph neural networks (GNNs) has shown promising results in various symbolic planning domains described by PDDL. However, existing approaches typically represent planning states as fully connected graphs, leading to a combinatorial explosion in edge information and substantial sparsity as problem scales grow, especially evident in large grid-based environments. This dense representation results in diluted node-level information, exponentially increases memory requirements, and ultimately makes learning infeasible for larger-scale problems. To address these challenges, we propose a sparse, goal-aware GNN representation that selectively encodes relevant local relationships and explicitly integrates spatial features related to the goal. We validate our approach by designing novel drone mission scenarios based on PDDL within a grid world, effectively simulating realistic mission execution environments. Our experimental results demonstrate that our method scales effectively to larger grid sizes previously infeasible with dense graph representations and substantially improves policy generalization and success rates. Our findings provide a practical foundation for addressing realistic, large-scale generalized planning tasks.
Abstract (translated)
使用深度强化学习(RL)与图神经网络(GNNs)相结合进行通用规划,在由PDDL描述的各种符号规划领域中取得了显著成果。然而,现有方法通常将规划状态表示为完全连接的图形,这导致随着问题规模的增长边缘信息组合爆炸和大量稀疏性,特别是在大型网格环境中尤为明显。这种密集表示法会稀释节点级别的信息,内存需求呈指数级增长,并最终使得大规模问题的学习变得不可行。为了应对这些挑战,我们提出了一种稀疏且目标感知的GNN表示方法,该方法选择性地编码相关的局部关系,并明确整合与目标相关的位置特征。通过在网格世界中基于PDDL设计新的无人机任务场景,以有效地模拟现实中的任务执行环境来验证我们的方法。实验结果表明,相对于密集图表示,我们的方法能够有效扩展到先前不可行的更大规模网格,并显著提高策略泛化能力和成功率。我们的研究为解决大规模通用规划的实际问题提供了实用基础。
URL
https://arxiv.org/abs/2508.10747