mlsanityData to 14 Oct 2026

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

arXiv 2508.10747 ↗First posted 14 Aug 2025cs.AI cs.ROcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 11 of its 39 references that are in the map. First posted on arXiv 14 Aug 2025.

Builds on

11 of 39 references.

References · 11

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  3. 2017Hindsight Experience Replaycited by 1,136
  4. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 337
  5. 2016Value Iteration Networkscited by 160
  6. 2020Generalized Planning With Deep Reinforcement Learningcited by 35
  7. 2022Safe Neurosymbolic Learning with Differentiable Symbolic Executioncited by 9
  8. 2024GraphScale: A Framework to Enable Machine Learning over Billion-node Graphscited by 4
  9. 2024Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planningcited by 3
  10. 2024Highway Value Iteration Networkscited by 2
  11. 2023Cooperative Multi-Agent Planning Framework for Fuel Constrained UAV-UGV Routing Problemcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Graph Based Deep Reinforcement Learning Aided by Transformers for Multi-Agent Cooperation
  2. 2020World Model as a Graph: Learning Latent Landmarks for Planning
  3. 2026Projecting Latent RL Actions: Towards Generalizable and Scalable Graph Combinatorial Optimization
  4. 2024Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning
  5. 2026Learning to Search and Searching to Learn for Generalization in Planning
  6. 2020Sparse Graphical Memory for Robust Planning
  7. 2025Horizon Generalization in Reinforcement Learning
  8. 2026On Sample-Efficient Generalized Planning via Learned Transition Models