RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Tasks (Extended Abstract)

• Published in: Proceedings of the International Symposium on Combinatorial Search Vol. 18; pp. 273 - 274
• Main Authors: Tang, Yimin, Xiong, Xiao, Xi, Jingyi, Li, Jiaoyang, Bıyık, Erdem, Koenig, Sven
• Format: Journal Article
• Language: English
• Published: 20.07.2025
• ISSN: 2832-9171; 2832-9163; 2832-9163
• DOI: 10.1609/socs.v18i1.36015

Multi-Agent Path Finding (MAPF), which focuses on finding collision-free paths for multiple robots, is crucial for applications ranging from aerial swarms to warehouse automation. Solving MAPF is NP-hard so learning-based approaches for MAPF have gained attention, particularly those leveraging deep neural networks. Nonetheless, despite the community's continued efforts, all learning-based MAPF planners still rely on decentralized planning due to variability in the number of agents and map sizes. We have developed the first centralized learning-based policy for MAPF problem called RAILGUN. RAILGUN is not an agent-based policy but a map-based policy. By leveraging a CNN-based architecture, RAILGUN can generalize across different maps and handle any number of agents. We collect trajectories from rule-based methods to train our model in a supervised way. In experiments, RAILGUN outperforms most baseline methods and demonstrates great zero-shot generalization capabilities on various tasks, maps and agent numbers that were not seen in the training dataset.