Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding

TL;DR

This review paper explores the integration of Deep Reinforcement Learning techniques in multi-agent pathfinding, emphasizing evaluation metrics, challenges, and future directions like model-based DRL for complex robotic environments.

Contribution

It provides a comprehensive overview of DRL-based MAPF approaches, highlights the need for unified evaluation metrics, and discusses the potential of model-based DRL as a future research avenue.

Findings

Highlights the integration of DRL in MAPF

Identifies the lack of unified evaluation metrics

Discusses potential of model-based DRL

Abstract

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.