Learning Efficiency Meets Symmetry Breaking
Not on the map. Why?
Abstract (arXiv)
Learning-based planners leveraging Graph Neural Networks can learn search guidance applicable to large search spaces, yet their potential to address symmetries remains largely unexplored. In this paper, we introduce a graph representation of planning problems allying learning efficiency with the ability to detect symmetries, along with two pruning methods, action pruning and state pruning, designed to manage symmetries during search. The integration of these techniques into Fast Downward achieves a first-time success over LAMA on the latest IPC learning track dataset. Code is released at: https://github.com/bybeye/Distincter.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 13 of its 36 references that are in the map. First posted on arXiv 28 Apr 2025.
Builds on
13 of 36 references.
References · 13
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
- 2019On the equivalence between graph isomorphism testing and function approximation with GNNscited by 172
- 2014The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarkscited by 87
- 2019Learning Domain-Independent Planning Heuristics with Hypergraph Networkscited by 50
- 2019ASNets: Deep Learning for Generalised Planningcited by 42
- 2021Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limitscited by 38
- 2023Learning Domain-Independent Heuristics for Grounded and Lifted Planningcited by 31
- 2024Return to Tradition: Learning Reliable Heuristics with Classical Machine Learningcited by 19
- 2023Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goalcited by 10
1 more
Built on by
Citing papers per year: 2026: 2.
2 papers.