SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding
Abstract
In this paper, we propose SCRIMP, a multi-agent reinforcement learning approach for multi-agent path finding. Our method learns individual policies from very small FOVs (3x3), by relying on a highly-scalable global/local communication mechanism based on a modified transformer. We further introduce a state-value-based tiebreaking strategy to improve performance in symmetric situations and intrinsic rewards to encourage exploration while mitigating the long-term credit assignment problem. Empirical evaluations indicate that SCRIMP can outperform other state-of-the-art learningbased planners with larger FOVs and even yield similar performance as a classical centralized planner.