authorea Authorea 10.36227/techrxiv.171084935.57702557/v3 0009-0009-7656-6522 Oh Seung Heon Byeon Geon Woong Cho Young In Kwon Seungmin Woo Jong Hun 4 3 2025 This preprint is available at https://doi.org/10.36227/techrxiv.171084935.57702557/v3 graph neural network reinforcement learning robotics and control systems weapon target assignment problem