mlsanityData to 14 Oct 2026

Learning Domain-Independent Planning Heuristics with Hypergraph Networks

arXiv 1911.13101 ↗First posted 29 Nov 2019cs.AI cs.LGcited by 50

Not on the map. Why?

Abstract (arXiv)

We present the first approach capable of learning domain-independent planning heuristics entirely from scratch. The heuristics we learn map the hypergraph representation of the delete-relaxation of the planning problem at hand, to a cost estimate that approximates that of the least-cost path from the current state to the goal through the hypergraph. We generalise Graph Networks to obtain a new framework for learning over hypergraphs, which we specialise to learn planning heuristics by training over state/value pairs obtained from optimal cost plans. Our experiments show that the resulting architecture, STRIPS-HGNs, is capable of learning heuristics that are competitive with existing delete-relaxation heuristics including LM-cut. We show that the heuristics we learn are able to generalise across different problems and domains, including to domains that were not seen during training.

Key facts. Cited by 50 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 14; 2023: 8; 2024: 8; 2025: 11; 2026: 4.

50 papers.

Sort:

By area:

  1. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 103
  2. 2024Can Graph Learning Improve Planning in LLM-based Agents?cited by 43
  3. 2023Learning Domain-Independent Heuristics for Grounded and Lifted Planningcited by 31
  4. 2021Classical Planning in Deep Latent Spacecited by 22
  5. 2022Learning Generalized Policies Without Supervision Using GNNscited by 22
  6. 2021Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generatorscited by 21
  7. 2024Return to Tradition: Learning Reliable Heuristics with Classical Machine Learningcited by 19
  8. 2025Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Codecited by 18
  9. 2022Learning Efficient Abstract Planning Models that Choose What to Predictcited by 17
  10. 2022Learning Sketches for Decomposing Planning Problems into Subproblems of Bounded Width: Extended Versioncited by 12
  11. 2023Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goalcited by 10
  12. 2021A Research Agenda for AI Planning in the Field of Flexible Production Systemscited by 8
38 more
  1. 2025Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policiescited by 7
  2. 2023NeSIG: A Neuro-Symbolic Method for Learning to Generate Planning Problemscited by 6
  3. 2023On Using Admissible Bounds for Learning Forward Search Heuristicscited by 5
  4. 2024Graph Learning for Numeric Planningcited by 5
  5. 2022Hierarchical Decomposition and Analysis for Generalized Planningcited by 4
  6. 2023Scale-Adaptive Balancing of Exploration and Exploitation in Classical Planningcited by 4
  7. 2024Towards Learning Foundation Models for Heuristic Functions to Solve Pathfinding Problemscited by 4
  8. 2025Leveraging Action Relational Structures for Integrated Learning and Planningcited by 4
  9. 2022Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planningcited by 3
  10. 2022Sampling from Pre-Images to Learn Heuristic Functions for Classical Planningcited by 3
  11. 2022Understanding Sample Generation Strategies for Learning Heuristic Functions in Classical Planningcited by 3
  12. 2024Graph Neural Network Based Action Ranking for Planningcited by 3
  13. 2025Learning General Policies with Policy Gradient Methodscited by 3
  14. 2021A* Search Without Expansions: Learning Heuristic Functions with Deep Q-Networkscited by 2
  15. 2021Meta-Reinforcement Learning for Heuristic Planningcited by 2
  16. 2022Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planningcited by 2
  17. 2022Hierarchical Reinforcement Learning with AI Planning Modelscited by 2
  18. 2022A Differentiable Loss Function for Learning Heuristics in A*cited by 2
  19. 2023A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Makingcited by 2
  20. 2023Learning Search-Space Specific Heuristics Using Neural Networkscited by 2
  21. 2024Deep Learning for Generalised Planning with Background Knowledgecited by 2
  22. 2025Counting and Reasoning with Planscited by 2
  23. 2025Learning Efficiency Meets Symmetry Breakingcited by 2
  24. 2025Weisfeiler-Leman Features for Planning: A 1,000,000 Sample Size Hyperparameter Studycited by 2
  25. 2025Learning Admissible Heuristics for A*: Theory and Practicecited by 2
  26. 2022Learning Visual Planning Models from Partially Observed Imagescited by 1
  27. 2024WLPlan: Relational Features for Symbolic Planningcited by 1
  28. 2022Learning to reason about and to act on physical cascading eventscited by 0
  29. 2022Scaling up ML-based Black-box Planning with Partial STRIPS Modelscited by 0
  30. 2022Abstract Interpretation for Generalized Heuristic Search in Model-Based Planningcited by 0
  31. 2024Graph Learning for Planning: The Story Thus Far and Open Challengescited by 0
  32. 2025LOOP: A Plug-and-Play Neuro-Symbolic Framework for Enhancing Planning in Autonomous Systemscited by 0
  33. 2025Symmetry-Invariant Novelty Heuristics via Unsupervised Weisfeiler-Leman Featurescited by 0
  34. 2025GammaZero: Learning To Guide POMDP Belief Space Search With Graph Representationscited by 0
  35. 2026Textual Planning with Explicit Latent Transitionscited by 0
  36. 2026On Sample-Efficient Generalized Planning via Learned Transition Modelscited by 0
  37. 2026Property-Guided LLM Program Synthesis for Planningcited by 0
  38. 2026Learning Admissible Heuristics via Cost Partitioningcited by 0