Research on Intelligent Decision Model Construction Based on Reinforcement Learning

In real-world combat scenarios, decisionmaking serves as the central dynamic between conflicting parties. The introduction of innovative technical means of decision support in combat situations is therefore of the utmost importance. Reinforcement learning algorithms offer the capability to optimize strategies through ongoing interaction with the environment, ultimately deriving the most effective action plan. This optimised strategy aims to improve command effectiveness by providing better support for commanders in making combat decisions. Our study focuses on historical war incidents in the Russian-Ukrainian conflict. We develop an intelligent decision-making system using the classical Q-learning algorithm in reinforcement learning. Taking into account the battlefield environment, the system uses input data to assess the basic condition of the troops of both factions. By evaluating the Q-values of each action in the resulting Q-table, the system provides training and decision-making suggestions. Ultimately, the goal is to provide valuable support to leaders to help them make informed combat decisions.