Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning

Multi-agent pathfinding (MAPF) is a common abstraction of multi-robot trajectory planning problems, where multiple homogeneous robots simultaneously move in the shared environment. While solving MAPF optimally has been proven to be NP-hard, scalable, and efficient, solvers are vital for real-world applications like logistics, search-and-rescue, etc. To this end, decentralized suboptimal MAPF solvers that leverage machine learning have come on stage. Building on the success of the recently introduced MAPF-GPT, a pure imitation learning solver, we introduce MAPF-GPT-DDG. This novel approach effectively fine-tunes the pre-trained MAPF model using centralized expert data. Leveraging a novel delta-data generation mechanism, MAPF-GPT-DDG accelerates training while significantly improving performance at test time. Our experiments demonstrate that MAPF-GPT-DDG surpasses all existing learning-based MAPF solvers, including the original MAPF-GPT, regarding solution quality across many testing scenarios. Remarkably, it can work with MAPF instances involving up to 1 million agents in a single environment, setting a new milestone for scalability in MAPF domains.

Authors

• Anton Andreychuk
• Konstantin S. Yakovlev
• Aleksandr Panov 0001
• Alexey Skrynnik

Keywords

• Training
• Trajectory planning
• Imitation learning
• Scalability
• Life estimation
• Data collection
• Data models
• Intelligent robots
• Testing
• Logistics
• Multi-Agent Path Finding
• Scalable
• Solution Quality
• Single Environment
• Leveraging Machine Learning
• Large Datasets
• Time Step
• Series Of Experiments
• Experimental Evaluation
• Stationary Distribution
• Online Learning
• Domain Shift
• Joint Action
• Number Of Agents
• Multi-agent Systems
• Random Function
• Collection Phase
• Policy Learning
• Types Of Maps
• Foundation Model
• Optimization Solver
• Cost Of Solution
• Real Robot
• Sequence Of Tokens