Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding
It provides a focused review and unified metrics for researchers in robotics and multi-agent systems, but is incremental as it synthesizes existing work rather than presenting new methods.
This review paper tackles the problem of integrating Deep Reinforcement Learning (DRL) into Multi-Agent Pathfinding (MAPF) by highlighting DRL-based approaches, addressing the lack of unified evaluation metrics, and discussing model-based DRL as a future direction to improve effectiveness in complex environments.
Multi-agent pathfinding (MAPF) is a critical field in many large-scale robotic applications, often being the fundamental step in multi-agent systems. The increasing complexity of MAPF in complex and crowded environments, however, critically diminishes the effectiveness of existing solutions. In contrast to other studies that have either presented a general overview of the recent advancements in MAPF or extensively reviewed Deep Reinforcement Learning (DRL) within multi-agent system settings independently, our work presented in this review paper focuses on highlighting the integration of DRL-based approaches in MAPF. Moreover, we aim to bridge the current gap in evaluating MAPF solutions by addressing the lack of unified evaluation metrics and providing comprehensive clarification on these metrics. Finally, our paper discusses the potential of model-based DRL as a promising future direction and provides its required foundational understanding to address current challenges in MAPF. Our objective is to assist readers in gaining insight into the current research direction, providing unified metrics for comparing different MAPF algorithms and expanding their knowledge of model-based DRL to address the existing challenges in MAPF.