Autonomous agents have been the center of discussion for the future concept of operations. Reinforcement learning (RL) is the core machine learning area for developing those intelligent agents, particularly in complex and dynamic environments such as battlefields and afflicted areas. This study proposes the large language model (LLM)-based RL system to utilize the power of LLMs for military RL applications. Users can use the system through prompts, and three different types of prompting are tested with the weapon selection scenario. The proposed system helps and guides users not only in building an RL agent (optimal policy) quickly but also in providing related theories and other information. In comparison to the human-designed RL system, the proposed system also had some limitations, such as reproducibility and reliability. This study discussed and suggested some remedies for the limitations.
SuttonRSBartoAG.Reinforcement learning: an introduction. 2nd ed. Cambridge, MA: MIT Press, 2018.
5.
AzarATKoubaaAMohamedNA, et al. Drone deep reinforcement learning: a review. Electronics2021; 10: 999.
6.
KochWMancusoRWestR, et al. Reinforcement learning for UAV attitude control. ACM Trans Cyber Phys Syst2019; 3: 1–21.
7.
QuCGaiWZhongM, et al. A novel reinforcement learning based grey wolf optimizer algorithm for unmanned aerial vehicles (UAVs) path planning. Appl Soft Comput2020; 89: 106099.
8.
HeLAoufNWhidborneJF, et al. Deep reinforcement learning based local planner for UAV obstacle avoidance using demonstration data. arXiv2020, https://arxiv.org/pdf/2008.02521
9.
WeiMWangSZhengJ, et al. UGV navigation optimization aided by reinforcement learning-based path tracking. IEEE Access2018; 6: 57814–57825.
10.
ChuZSunBZhuD, et al. Motion control of unmanned underwater vehicles via deep imitation reinforcement learning algorithm. IET Intell Transp Syst2020; 14: 764–774.
11.
AdawadkarAMKKulkarniN. Cyber-security and reinforcement learning—a brief survey. Eng Appl Artif Intell2022; 114: 105116.
12.
SewakMSahaySRathoreH.DRLDO a novel DRL based de obfuscation system for defence against metamorphic malware. Def Sci J2021; 71: 55–65.
HeartfieldRLoukasGBezemskijA, et al. Self-configurable cyber-physical intrusion detection for smart homes using reinforcement learning. IEEE Trans Inf Forensics Secur2021; 16: 1720–1735.
15.
FerdowsiASaadW.Deep learning for signal authentication and security in massive Internet-of-Things systems. IEEE Trans Wirel Commun2019; 67: 1371–1387.
16.
LuXXiaoLXuT, et al. Reinforcement learning based PHY authentication for VANETs. IEEE Trans Veh Technol2020; 69: 3068–3079.
17.
BoronJDarkenC. Developing combat behavior through reinforcement learning in war-games and simulations. In: Proceedings of 2020 IEEE conference on games (CoG), Osaka, Japan, 24–27 August 2020, pp. 728–731. New York: IEEE.
18.
ZhangLAXuJGoldD, et al. Air dominance through ma-chine learning: a preliminary exploration of artificial intelligence–assisted mission planning. Santa Monica, CA: RAND Corporation, 2020.
19.
SoleymanSKhoslaD.Multi-agent mission planning with reinforcement learning. In: Proceedings of AAAI symposium on the 2nd work-shop on deep models and artificial intelligence for defense applications: potentials, theories, practices, tools, and risks, virtual, 11–12 November 2020.
20.
FuQFanCLSongY, et al. Alpha C2–an intelligent air defense commander in-dependent of human decision-making. IEEE Access2020; 8: 87504–87516.
21.
GoecksVGWaytowichNAsherDE, et al. On games and simulators as a platform for development of artificial intelligence for command and control. J Def Model Simul2022; 20: 495–508.
22.
YouSDiaoMGaoL.Deep reinforcement learning for target searching in cognitive electronic warfare. IEEE Access2019; 7: 37432–37447.
23.
HuaWFanLLiL, et al. War and peace (WarAgent): large language model-based multi-agent simulation of world wars. arXiv 2024, https://arxiv.org/pdf/2311.17227
24.
GoecksVGWaytowichN.COA-GPT: generative pre-trained transformers for accelerated course of action development in military operations. arXiv 2024, https://arxiv.org/pdf/2402.01786
25.
GoecksVGWaytowichN.DisasterResponseGPT: large language models for accelerated plan of action development in disaster response scenarios. arXiv 2023, https://arxiv.org/pdf/2306.17271
26.
WeiJWangXSchuurmansD, et al. Chain-of-thought prompting elicits reasoning in large language models. arXiv 2023, https://arxiv.org/pdf/2201.11903
27.
YaoSYuDZhaoJ, et al. Tree of thoughts: deliberate problem solving with large language models. arXiv2023, https://arxiv.org/pdf/2305.10601
