Paper Reading AI Learner

Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning

2025-08-14 15:30:28
Sangwoo Jeon, Juchul Shin, Gyeong-Tae Kim, YeonJe Cho, Seongwoo Kim

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

PDF

https://arxiv.org/pdf/2508.10747.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot