HiMAP: Learning Heuristics-Informed Policies for Large-Scale Multi-Agent Pathfinding

arXiv:2402.15546v1 Announce Type: cross
Abstract: Large-scale multi-agent pathfinding (MAPF) presents significant challenges in several areas. As systems grow in complexity with a multitude of autonomous agents operating simultaneously, efficient and collision-free coordination becomes paramount. Traditional algorithms often fall short in scalability, especially in intricate scenarios. Reinforcement Learning (RL) has shown potential to address the intricacies of MAPF; however, it has also been shown to struggle with scalability, demanding intricate implementation, lengthy training, and often exhibiting unstable convergence, limiting its practical …

abstract agent agents algorithms arxiv autonomous autonomous agents challenges collision complexity cs.ai cs.lg cs.ma cs.ro free heuristics multi-agent pathfinding reinforcement reinforcement learning scalability scale systems type