mlsanityData to 7 Oct 2026

Graph Learning for Numeric Planning

arXiv 2410.24080 ↗First posted 31 Oct 2024cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Graph learning is naturally well suited for use in symbolic, object-centric planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary numbers of objects. Numeric planning is an extension of symbolic planning in which states may now also exhibit numeric variables. In this work, we propose data-efficient and interpretable machine learning models for learning to solve numeric planning tasks. This involves constructing a new graph kernel for graphs with both continuous and categorical attributes, as well as new optimisation methods for learning heuristic functions for numeric planning. Experiments show that our graph kernels are vastly more efficient and generalise better than graph neural networks for numeric planning, and also yield competitive coverage performance compared to domain-independent numeric planners. Code is available at https://github.com/DillonZChen/goose

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 33 of its 78 references that are in the map. First posted on arXiv 31 Oct 2024.

Builds on

33 of 78 references.

References · 33

  1. 2018How Powerful are Graph Neural Networks?cited by 4,355
  2. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  3. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  4. 2020Reward Machines: Exploiting Reward Function Structure in Reinforcement Learningcited by 183
  5. 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
  6. 2019Wasserstein Weisfeiler-Lehman Graph Kernelscited by 104
  7. 2019Learning Domain-Independent Planning Heuristics with Hypergraph Networkscited by 50
  8. 2022Predicate Invention for Bilevel Planningcited by 49
  9. 2019ASNets: Deep Learning for Generalised Planningcited by 42
  10. 2020Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networkscited by 38
  11. 2021Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limitscited by 38
  12. 2016Faster Kernels for Graphs with Continuous Attributes via Hashingcited by 31
21 more
  1. 2023Learning Domain-Independent Heuristics for Grounded and Lifted Planningcited by 31
  2. 2018Features, Projections, and Representation Change for Generalized Planningcited by 25
  3. 2016Learning to Rank for Synthesizing Planning Heuristicscited by 22
  4. 2020Learning Generalized Relational Heuristic Networks for Model-Agnostic Planningcited by 22
  5. 2021Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generatorscited by 21
  6. 2024Return to Tradition: Learning Reliable Heuristics with Classical Machine Learningcited by 19
  7. 2019Qualitative Numeric Planning: Reductions and Complexitycited by 18
  8. 2021Generalized Planning as Heuristic Searchcited by 18
  9. 2022DANLI: Deliberative Agent for Following Natural Language Instructionscited by 15
  10. 2018Model-free, Model-based, and General Intelligencecited by 14
  11. 2022Scaling-up Generalized Planning as Heuristic Search with Landmarkscited by 14
  12. 2018Online Planner Selection with Graph Neural Networks and Adaptive Schedulingcited by 13
  13. 2023Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goalcited by 10
  14. 2023What Planning Problems Can A Relational Neural Network Solve?cited by 8
  15. 2023Egocentric Planning for Scalable Embodied Task Achievementcited by 7
  16. 2024Novelty Heuristics, Multi-Queue Search, and Portfolios for Numeric Planningcited by 6
  17. 2022Hierarchical Decomposition and Analysis for Generalized Planningcited by 4
  18. 2021Online Grounding of Symbolic Planning Domains in Unknown Environmentscited by 3
  19. 2023PushWorld: A benchmark for manipulation planning with tools and movable obstaclescited by 3
  20. 2014A Hybrid LP-RPG Heuristic for Modelling Numeric Resource Flows in Planningcited by 2
  21. 2024Deep Learning for Generalised Planning with Background Knowledgecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 2.

5 papers.

  1. 2025Weisfeiler-Leman Features for Planning: A 1,000,000 Sample Size Hyperparameter Studycited by 2
  2. 2025Vejde: A Framework for Inductive Deep Reinforcement Learning Based on Factor Graph Color Refinementcited by 2
  3. 2024Graph Learning for Planning: The Story Thus Far and Open Challengescited by 0
  4. 2026Learning to Search and Searching to Learn for Generalization in Planningcited by 0
  5. 2026Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraintscited by 0