# Graph Learning for Planning: The Story Thus Far and Open Challenges

arXiv: https://arxiv.org/abs/2412.02136 · HTML: https://mlsanity.com/paper/2412.02136/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 80 references that are in the map.
- First posted on arXiv 3 Dec 2024.

## Builds on (most cited first, 30 of 36)

- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks](https://mlsanity.com/paper/1810.02244/) (2018)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting](https://mlsanity.com/paper/2006.09252/) (2020)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [The Surprising Power of Graph Neural Networks with Random Node Initialization](https://mlsanity.com/paper/2010.01179/) (2020)
- [From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness](https://mlsanity.com/paper/2110.03753/) (2021)
- [A Survey on Graph Kernels](https://mlsanity.com/paper/1903.11835/) (2019)
- [Neural Logic Machines](https://mlsanity.com/paper/1904.11694/) (2019)
- [Breaking the Limits of Message Passing Graph Neural Networks](https://mlsanity.com/paper/2106.04319/) (2021)
- [LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench](https://mlsanity.com/paper/2409.13373/) (2024)
- [How Powerful are K-hop Message Passing Graph Neural Networks](https://mlsanity.com/paper/2205.13328/) (2022)
- [The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarks](https://mlsanity.com/paper/1401.3839/) (2014)
- [The Logic of Graph Neural Networks](https://mlsanity.com/paper/2104.14624/) (2021)
- [Learning Domain-Independent Planning Heuristics with Hypergraph Networks](https://mlsanity.com/paper/1911.13101/) (2019)
- [Inductive logic programming at 30](https://mlsanity.com/paper/2102.10556/) (2021)
- [Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks](https://mlsanity.com/paper/2009.05613/) (2020)
- [Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits](https://mlsanity.com/paper/2109.10129/) (2021)
- [SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks](https://mlsanity.com/paper/2203.13913/) (2022)
- [Action Schema Networks: Generalised Policies with Deep Learning](https://mlsanity.com/paper/1709.04271/) (2017)
- [Learning Domain-Independent Heuristics for Grounded and Lifted Planning](https://mlsanity.com/paper/2312.11143/) (2023)
- [Learning to Rank for Synthesizing Planning Heuristics](https://mlsanity.com/paper/1608.01302/) (2016)
- [Learning Generalized Relational Heuristic Networks for Model-Agnostic Planning](https://mlsanity.com/paper/2007.06702/) (2020)
- [Policy-Guided Heuristic Search with Guarantees](https://mlsanity.com/paper/2103.11505/) (2021)
- [A Practical, Progressively-Expressive GNN](https://mlsanity.com/paper/2210.09521/) (2022)
- [Return to Tradition: Learning Reliable Heuristics with Classical Machine Learning](https://mlsanity.com/paper/2403.16508/) (2024)
- [Online Planner Selection with Graph Neural Networks and Adaptive Scheduling](https://mlsanity.com/paper/1811.00210/) (2018)
- [Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goal](https://mlsanity.com/paper/2310.19463/) (2023)
- [What Planning Problems Can A Relational Neural Network Solve?](https://mlsanity.com/paper/2312.03682/) (2023)

## Abstract (arXiv)

Graph learning is naturally well suited for use in planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary number of objects. In this paper, we study the usage of graph learning for planning thus far by studying the theoretical and empirical effects on learning and planning performance of (1) graph representations of planning tasks, (2) graph learning architectures, and (3) optimisation formulations for learning. Our studies accumulate in the GOOSE framework which learns domain knowledge from small planning tasks in order to scale up to much larger planning tasks. In this paper, we also highlight and propose the 5 open challenges in the general Learning for Planning field that we believe need to be addressed for advancing the state-of-the-art.