APPLICATION OF ARTIFICIAL INTELLIGENCE BASED SIMULATIONS FOR MILITARY LOGISTICS SUPPLY NETWORK DECISION MAKING

This paper discusses the application of Artificial Intelligence-based simulations currently used by the video gaming industry to evaluate decisions common to a military logistics supply network (MLSN). MLSNs have an array of challenges, some which are comparable to commercial logistic networks such as balancing resources and time-constrained decision making. The two greatly differ in the degree and frequency of dynamic shifts that may occur mission to mission. This causes a high level of uncertainty to an already complex field of study. Additionally, these decision makers operate under duress or crisis while bearing the fact that the decisions, if made incorrectly, can cost lives.

The case study in this paper provides computer-generated solutions to select MLSN missions. By employing current gaming technologies, decision science, and simulation techniques we show in great detail how the computer solves the mission, action by action; why it eliminates scenarios and what options are feasible. In doing so, unit commanders can utilize the concept of reinforcement learning in day-to-day missions or carryout training objectives with potential coalition partners providing visualization, decision support, what-if analysis, or problem simplification by eliminating scenarios that do not achieve the overall mission goals or violate constraints.