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

arXiv: https://arxiv.org/abs/2508.10747 · HTML: https://mlsanity.com/paper/2508.10747/

## 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.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 11 of 11)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [FeUdal Networks for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1703.01161/) (2017)
- [Value Iteration Networks](https://mlsanity.com/paper/1602.02867/) (2016)
- [Generalized Planning With Deep Reinforcement Learning](https://mlsanity.com/paper/2005.02305/) (2020)
- [Safe Neurosymbolic Learning with Differentiable Symbolic Execution](https://mlsanity.com/paper/2203.07671/) (2022)
- [GraphScale: A Framework to Enable Machine Learning over Billion-node Graphs](https://mlsanity.com/paper/2407.15452/) (2024)
- [Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning](https://mlsanity.com/paper/2406.08404/) (2024)
- [Highway Value Iteration Networks](https://mlsanity.com/paper/2406.03485/) (2024)
- [Cooperative Multi-Agent Planning Framework for Fuel Constrained UAV-UGV Routing Problem](https://mlsanity.com/paper/2309.03397/) (2023)

## 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.