スケールアップしても薄まらない:RLベース汎用計画のためのゴール認識スパースGNN
Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning
PDDLで記述された計画問題を強化学習とグラフニューラルネットワークで解く際、状態を全結合グラフで表すと大規模環境で情報が薄まり学習が困難になる問題に対し、局所関係とゴール関連の空間特徴を選択的に符号化するスパースでゴール認識型のGNN表現を提案し、大規模グリッドでのドローンミッション計画で有効性を示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Sangwoo Jeon, Juchul Shin, Gyeong-Tae Kim, YeonJe Cho, Seongwoo Kim
分類: cs.AI, cs.RO
原文アブストラクト
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.
