mlsanityData to 7 Oct 2026

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

arXiv 2412.02136 ↗First posted 3 Dec 2024cs.AIcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 80 references that are in the map. First posted on arXiv 3 Dec 2024.

Builds on

36 of 80 references.

References · 36

  1. 2018How Powerful are Graph Neural Networks?cited by 4,355
  2. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  3. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  4. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 372
  5. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 312
  6. 2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 308
  7. 2020The Surprising Power of Graph Neural Networks with Random Node Initializationcited by 190
  8. 2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 154
  9. 2019A Survey on Graph Kernelscited by 148
  10. 2019Neural Logic Machinescited by 144
  11. 2021Breaking the Limits of Message Passing Graph Neural Networkscited by 101
  12. 2024LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBenchcited by 93
24 more
  1. 2022How Powerful are K-hop Message Passing Graph Neural Networkscited by 90
  2. 2014The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarkscited by 86
  3. 2021The Logic of Graph Neural Networkscited by 84
  4. 2019Learning Domain-Independent Planning Heuristics with Hypergraph Networkscited by 50
  5. 2021Inductive logic programming at 30cited by 46
  6. 2020Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networkscited by 38
  7. 2021Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limitscited by 38
  8. 2022SpeqNets: Sparsity-aware Permutation-equivariant Graph Networkscited by 37
  9. 2017Action Schema Networks: Generalised Policies with Deep Learningcited by 32
  10. 2023Learning Domain-Independent Heuristics for Grounded and Lifted Planningcited by 31
  11. 2016Learning to Rank for Synthesizing Planning Heuristicscited by 22
  12. 2020Learning Generalized Relational Heuristic Networks for Model-Agnostic Planningcited by 22
  13. 2021Policy-Guided Heuristic Search with Guaranteescited by 20
  14. 2022A Practical, Progressively-Expressive GNNcited by 20
  15. 2024Return to Tradition: Learning Reliable Heuristics with Classical Machine Learningcited by 19
  16. 2018Online Planner Selection with Graph Neural Networks and Adaptive Schedulingcited by 13
  17. 2023Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goalcited by 10
  18. 2023What Planning Problems Can A Relational Neural Network Solve?cited by 8
  19. 2023General Policies, Subgoal Structure, and Planning Widthcited by 6
  20. 2024Novelty Heuristics, Multi-Queue Search, and Portfolios for Numeric Planningcited by 6
  21. 2023On Using Admissible Bounds for Learning Forward Search Heuristicscited by 5
  22. 2024Graph Learning for Numeric Planningcited by 5
  23. 2023Improving Subgraph-GNNs via Edge-Level Ego-Network Encodingscited by 4
  24. 2024Deep Learning for Generalised Planning with Background Knowledgecited by 2

Built on by

Not cited yet.