ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.11721
23
0

Relational GNNs Cannot Learn C2C_2C2​ Features for Planning

13 June 2025
Dillon Z. Chen
ArXiv (abs)PDFHTML
Main:3 Pages
1 Figures
Bibliography:1 Pages
Abstract

Relational Graph Neural Networks (R-GNNs) are a GNN-based approach for learning value functions that can generalise to unseen problems from a given planning domain. R-GNNs were theoretically motivated by the well known connection between the expressive power of GNNs and C2C_2C2​, first-order logic with two variables and counting. In the context of planning, C2C_2C2​ features refer to the set of formulae in C2C_2C2​ with relations defined by the unary and binary predicates of a planning domain. Some planning domains exhibit optimal value functions that can be decomposed as arithmetic expressions of C2C_2C2​ features. We show that, contrary to empirical results, R-GNNs cannot learn value functions defined by C2C_2C2​ features. We also identify prior GNN architectures for planning that may better learn value functions defined by C2C_2C2​ features.

View on arXiv
@article{chen2025_2506.11721,
  title={ Relational GNNs Cannot Learn $C_2$ Features for Planning },
  author={ Dillon Z. Chen },
  journal={arXiv preprint arXiv:2506.11721},
  year={ 2025 }
}
Comments on this paper