mlsanityData to 14 Oct 2026

Learning Domain-Independent Heuristics for Grounded and Lifted Planning

arXiv 2312.11143 ↗First posted 18 Dec 2023cs.AIcited by 31

Not on the map. Why?

Abstract (arXiv)

We present three novel graph representations of planning tasks suitable for learning domain-independent heuristics using Graph Neural Networks (GNNs) to guide search. In particular, to mitigate the issues caused by large grounded GNNs we present the first method for learning domain-independent heuristics with only the lifted representation of a planning task. We also provide a theoretical analysis of the expressiveness of our models, showing that some are more powerful than STRIPS-HGN, the only other existing model for learning domain-independent heuristics. Our experiments show that our heuristics generalise to much larger problems than those in the training set, vastly surpassing STRIPS-HGN heuristics.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 17 of its 39 references that are in the map. First posted on arXiv 18 Dec 2023.

Builds on

17 of 39 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  4. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  5. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  6. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 333
  7. 2020The Surprising Power of Graph Neural Networks with Random Node Initializationcited by 198
  8. 2019Neural Logic Machinescited by 145
  9. 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
  10. 2014The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarkscited by 87
  11. 2019Learning Domain-Independent Planning Heuristics with Hypergraph Networkscited by 50
  12. 2019ASNets: Deep Learning for Generalised Planningcited by 42
5 more
  1. 2021Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limitscited by 38
  2. 2020Learning Generalized Relational Heuristic Networks for Model-Agnostic Planningcited by 22
  3. 2022Learning Generalized Policies Without Supervision Using GNNscited by 22
  4. 2021Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generatorscited by 21
  5. 2018Online Planner Selection with Graph Neural Networks and Adaptive Schedulingcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 11; 2025: 14; 2026: 6.

31 papers.

Sort:

By area:

  1. 2024Can Graph Learning Improve Planning in LLM-based Agents?cited by 43
  2. 2024Return to Tradition: Learning Reliable Heuristics with Classical Machine Learningcited by 19
  3. 2025Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Codecited by 18
  4. 2025Successor-Generator Planning with LLM-generated Heuristicscited by 7
  5. 2025Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policiescited by 7
  6. 2024Graph Learning for Numeric Planningcited by 5
  7. 2024HBTP: Heuristic Behavior Tree Planning with Large Language Model Reasoningcited by 4
  8. 2024Towards Learning Foundation Models for Heuristic Functions to Solve Pathfinding Problemscited by 4
  9. 2025Leveraging Action Relational Structures for Integrated Learning and Planningcited by 4
  10. 2025CoS: Towards Optimal Event Scheduling via Chain-of-Schedulingcited by 4
  11. 2024PDDLFuse: A Tool for Generating Diverse Planning Domainscited by 3
  12. 2024Graph Neural Network Based Action Ranking for Planningcited by 3
19 more
  1. 2024Deep Learning for Generalised Planning with Background Knowledgecited by 2
  2. 2025Counting and Reasoning with Planscited by 2
  3. 2025Learning Efficiency Meets Symmetry Breakingcited by 2
  4. 2025Weisfeiler-Leman Features for Planning: A 1,000,000 Sample Size Hyperparameter Studycited by 2
  5. 2025Learning Admissible Heuristics for A*: Theory and Practicecited by 2
  6. 2024Choosing a Classical Planner with Graph Neural Networkscited by 1
  7. 2024WLPlan: Relational Features for Symbolic Planningcited by 1
  8. 2026LLM-Evolved Domain-Independent Heuristics for Symbolic AI Planningcited by 1
  9. 2024Graph Learning for Planning: The Story Thus Far and Open Challengescited by 0
  10. 2025Exploiting Symbolic Heuristics for the Synthesis of Domain-Specific Temporal Planning Guidance using Reinforcement Learningcited by 0
  11. 2025Relational GNNs Cannot Learn C2 Features for Planningcited by 0
  12. 2025Symmetry-Invariant Novelty Heuristics via Unsupervised Weisfeiler-Leman Featurescited by 0
  13. 2025From domain-landmark graph learning to problem-landmark graph generationcited by 0
  14. 2025Two Constraint Compilation Methods for Lifted Planningcited by 0
  15. 2026Per-Domain Generalizing Policies: On Learning Efficient and Robust Q-Value Functions (Extended Version with Technical Appendix)cited by 0
  16. 2026Property-Guided LLM Program Synthesis for Planningcited by 0
  17. 2026Learning to Search and Searching to Learn for Generalization in Planningcited by 0
  18. 2026LLM-Evolved Pattern Generators for Optimal Classical Planningcited by 0
  19. 2026Learning Admissible Heuristics via Cost Partitioningcited by 0