Academic Journal

Learning Efficiency Meets Symmetry Breaking

Bibliographic Details
Title: Learning Efficiency Meets Symmetry Breaking
Authors: Bai, Yingbin, Thiébaux, Sylvie, Trevizan, Felipe
Contributors: Thiébaux, Sylvie
Source: Proceedings of the International Conference on Automated Planning and Scheduling. 35:154-159
Publication Status: Preprint
Publisher Information: Association for the Advancement of Artificial Intelligence (AAAI), 2025.
Publication Year: 2025
Subject Terms: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Machine Learning (cs.LG)
Description: 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.
Document Type: Article
Conference object
File Description: application/pdf
ISSN: 2334-0843
2334-0835
DOI: 10.1609/icaps.v35i1.36112
DOI: 10.48550/arxiv.2504.19738
Access URL: http://arxiv.org/abs/2504.19738
https://hal.science/hal-05226738v1
Rights: CC BY
Accession Number: edsair.doi.dedup.....0c37dfa07b0481f37267837103e096b3
Database: OpenAIRE
Description
ISSN:23340843
23340835
DOI:10.1609/icaps.v35i1.36112