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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jeon, Sangwoo, Shin, Juchul, Kim, Gyeong-Tae, Cho, YeonJe, Kim, Seongwoo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909893740462080
author Jeon, Sangwoo
Shin, Juchul
Kim, Gyeong-Tae
Cho, YeonJe
Kim, Seongwoo
author_facet Jeon, Sangwoo
Shin, Juchul
Kim, Gyeong-Tae
Cho, YeonJe
Kim, Seongwoo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10747
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning
Jeon, Sangwoo
Shin, Juchul
Kim, Gyeong-Tae
Cho, YeonJe
Kim, Seongwoo
Artificial Intelligence
Robotics
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.
title Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning
topic Artificial Intelligence
Robotics
url https://arxiv.org/abs/2508.10747