@article{MD083A322,
title = "A Survey on Weapon-Target Assignment for Realistic Battlefield Environments: From Exact Algorithm to Deep Reinforcement Learning",
journal = "The Journal of Korean Institute of Communications and Information Sciences",
year = "2025",
issn = "1226-4717",
doi = "10.7840/kics.2025.50.2.205",
author = "Chanin Eom, Jaehwi Lee, Minhae Kwon",
keywords = "Military decision-making, Weapon-target assignment, Intelligent command decision, Deep reinforcement learning, Heuristic algorithm",
abstract = "As the demand for intelligent command decision support systems grows, significant attention has been directed toward military decision-making. Weapon-target assignment (WTA) is a key component of a commander’s decision-making process, playing a crucial role in executing effective attacks and efficiently managing resources.
Recently, WTA research has evolved to address realistic modern battlefield environments, increasing the complexity of optimization. For this reason, much WTA research has focused on time-efficient approaches, e.g., heuristic algorithms or deep reinforcement learning. Among these methods, deep reinforcement learning has garnered remarkable attention due to its high generalization performance in complex environments. In this paper, we survey research trends in WTA studies, a key component of intelligent military decision-making. Furthermore, we propose future directions for enhancing WTA systems to better address realistic battlefield environments."
}