Learning Efficiency Meets Symmetry Breaking
This addresses symmetry breaking in planning for AI researchers, but it is incremental as it builds on existing methods like Fast Downward.
The paper tackles the problem of symmetry in learning-based planners by introducing a graph representation and pruning methods, achieving first-time success over LAMA on the latest IPC learning track dataset.
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.