关键词: 装备体系, 作战效能评估, 多智能体博弈强化学习, 最优策略

Abstract:

The equipment system is the reflection of the combat system from the perspective of equipment. The research on the combat effectiveness evaluation of the equipment system is of great practical significance for the optimization, construction, and development of the equipment system. Cluster equipment combat system confrontation is characterized by large-scale, highly dynamic and strong confrontation, and it is difficult to directly evaluate combat effectiveness with traditional methods. Aiming at the single task homogeneous cluster equipment system (such as UAV reconnaissance swarm and ground unmanned platform fire assault cluster), this paper regards the confrontation process of equipment system as the Markov game process of multi-agent system from the perspective of multi-agent game theory. The combat effectiveness evaluation method of equipment system based on reinforcement learning of multi-agent game (RLoMAG) is proposed. Firstly, the principle of evaluation method is analyzed and the model of equipment system confrontation is built. Secondly, the framework of the combat effectiveness evaluation method of the equipment system is given, including conducting the agent modeling, game algorithm design and combat effectiveness index design of the equipment system, carrying out exploratory system confrontation simulation, solving the game optimal strategy of the equipment system, and analyzing the combat effectiveness index of the equipment system under the optimal strategy. Finally, based on the base defense combat scenario, an application example of the combat effectiveness evaluation method of the UAV swarm equipment system is given to verify the effectiveness of the method.

Key words: equipment system, combat effectiveness evaluation, reinforcement learning of multi-agent game, optimum strategy